Duplicate from MarsupialAI/Aqueducts-18B_exl2

Co-authored-by: Nonya Biznez <MarsupialAI@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

2.5bpw/config.json

@@ -0,0 +1,39 @@
+{
+    "_name_or_path": "f:\\Aqueducts\\Thermae",
+    "antemplate": "[Genre: <|>]",
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.40.0.dev0",
+    "use_cache": false,
+    "vocab_size": 32000,
+    "welcome": "## Warning: This model has a very heavy NSFW bias and is not suitable for use by minors!\n\nYou are currently running story-writing model `Erebus, version 3 (Mistral 7B).`\n\n This model is made by [Mr. Seeker](https://www.patreon.com/mrseeker) with help of ProudNoob and the KoboldAI team.\n\n### How to use this model\n\nErebus is designed to generate short stories and novels. Use the author's note to give it a certain genre to follow, use memory to give an overview of the story and use World Information to give specific details about the characters. To start off, give the AI an idea of what you are writing about by setting the scene. Give the AI around 10 sentences that make your story interesting to read. Introduce your character, describe the world, blow something up, or let the AI use its creative mind.",
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.18",
+        "bits": 2.5,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

2.5bpw/mergekit_config.yml

@@ -0,0 +1,12 @@
+dtype: float16
+merge_method: linear
+slices:
+- sources:
+  - layer_range: [0, 80]
+    model: f:\Aqueducts\Thermae
+    parameters:
+      weight: 0.5
+  - layer_range: [0, 80]
+    model: f:\Aqueducts\Circuses
+    parameters:
+      weight: 0.5

2.5bpw/model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 35422216192}, "weight_map": {"lm_head.weight": "model-00001-of-00004.safetensors", "model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors"}}

2.5bpw/output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3673855e0150ac383c3f14aa85006471fc7aa4eacda576a463f93bb7c7f517
+size 5820342964

2.5bpw/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

2.5bpw/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

2.5bpw/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

3.5bpw/config.json

@@ -0,0 +1,39 @@
+{
+    "_name_or_path": "f:\\Aqueducts\\Thermae",
+    "antemplate": "[Genre: <|>]",
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.40.0.dev0",
+    "use_cache": false,
+    "vocab_size": 32000,
+    "welcome": "## Warning: This model has a very heavy NSFW bias and is not suitable for use by minors!\n\nYou are currently running story-writing model `Erebus, version 3 (Mistral 7B).`\n\n This model is made by [Mr. Seeker](https://www.patreon.com/mrseeker) with help of ProudNoob and the KoboldAI team.\n\n### How to use this model\n\nErebus is designed to generate short stories and novels. Use the author's note to give it a certain genre to follow, use memory to give an overview of the story and use World Information to give specific details about the characters. To start off, give the AI an idea of what you are writing about by setting the scene. Give the AI around 10 sentences that make your story interesting to read. Introduce your character, describe the world, blow something up, or let the AI use its creative mind.",
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.18",
+        "bits": 3.5,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

3.5bpw/mergekit_config.yml

@@ -0,0 +1,12 @@
+dtype: float16
+merge_method: linear
+slices:
+- sources:
+  - layer_range: [0, 80]
+    model: f:\Aqueducts\Thermae
+    parameters:
+      weight: 0.5
+  - layer_range: [0, 80]
+    model: f:\Aqueducts\Circuses
+    parameters:
+      weight: 0.5

3.5bpw/model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 35422216192}, "weight_map": {"lm_head.weight": "model-00001-of-00004.safetensors", "model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors"}}

3.5bpw/output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d300a0ac527ff7f3338974a78984617bf79cb3e1d12686ea33bdea8dfc72382
+size 8001222996

3.5bpw/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

3.5bpw/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

3.5bpw/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

4.5bpw/config.json

@@ -0,0 +1,39 @@
+{
+    "_name_or_path": "f:\\Aqueducts\\Thermae",
+    "antemplate": "[Genre: <|>]",
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.40.0.dev0",
+    "use_cache": false,
+    "vocab_size": 32000,
+    "welcome": "## Warning: This model has a very heavy NSFW bias and is not suitable for use by minors!\n\nYou are currently running story-writing model `Erebus, version 3 (Mistral 7B).`\n\n This model is made by [Mr. Seeker](https://www.patreon.com/mrseeker) with help of ProudNoob and the KoboldAI team.\n\n### How to use this model\n\nErebus is designed to generate short stories and novels. Use the author's note to give it a certain genre to follow, use memory to give an overview of the story and use World Information to give specific details about the characters. To start off, give the AI an idea of what you are writing about by setting the scene. Give the AI around 10 sentences that make your story interesting to read. Introduce your character, describe the world, blow something up, or let the AI use its creative mind.",
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.18",
+        "bits": 4.5,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

4.5bpw/mergekit_config.yml

@@ -0,0 +1,12 @@
+dtype: float16
+merge_method: linear
+slices:
+- sources:
+  - layer_range: [0, 80]
+    model: f:\Aqueducts\Thermae
+    parameters:
+      weight: 0.5
+  - layer_range: [0, 80]
+    model: f:\Aqueducts\Circuses
+    parameters:
+      weight: 0.5

4.5bpw/model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 35422216192}, "weight_map": {"lm_head.weight": "model-00001-of-00004.safetensors", "model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors"}}

4.5bpw/output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2417cd1ae0140f9e7c907ca8aa7e02de0d035702cf6bfbc30cae4d60fbd807ef
+size 8589711480

4.5bpw/output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add6d96bddc9113f1ed7cd4ff27628c827e0a5da6f4206e438115723fcaa435a
+size 1592702192

4.5bpw/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

4.5bpw/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

4.5bpw/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

5.5bpw/config.json

@@ -0,0 +1,39 @@
+{
+    "_name_or_path": "f:\\Aqueducts\\Thermae",
+    "antemplate": "[Genre: <|>]",
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.40.0.dev0",
+    "use_cache": false,
+    "vocab_size": 32000,
+    "welcome": "## Warning: This model has a very heavy NSFW bias and is not suitable for use by minors!\n\nYou are currently running story-writing model `Erebus, version 3 (Mistral 7B).`\n\n This model is made by [Mr. Seeker](https://www.patreon.com/mrseeker) with help of ProudNoob and the KoboldAI team.\n\n### How to use this model\n\nErebus is designed to generate short stories and novels. Use the author's note to give it a certain genre to follow, use memory to give an overview of the story and use World Information to give specific details about the characters. To start off, give the AI an idea of what you are writing about by setting the scene. Give the AI around 10 sentences that make your story interesting to read. Introduce your character, describe the world, blow something up, or let the AI use its creative mind.",
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.18",
+        "bits": 5.5,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

5.5bpw/mergekit_config.yml

@@ -0,0 +1,12 @@
+dtype: float16
+merge_method: linear
+slices:
+- sources:
+  - layer_range: [0, 80]
+    model: f:\Aqueducts\Thermae
+    parameters:
+      weight: 0.5
+  - layer_range: [0, 80]
+    model: f:\Aqueducts\Circuses
+    parameters:
+      weight: 0.5

5.5bpw/model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 35422216192}, "weight_map": {"lm_head.weight": "model-00001-of-00004.safetensors", "model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors"}}

5.5bpw/output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b64907cee559045aa292adcaf9da09707520cf84fe50c6468c29ee2b1f17fe
+size 8567105944

5.5bpw/output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebc18f604647ea7905b81fcaf8de858498b6d903426655c9846d09345cc6b56
+size 3794618352

5.5bpw/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

5.5bpw/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

5.5bpw/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

6.5bpw/config.json

@@ -0,0 +1,39 @@
+{
+    "_name_or_path": "f:\\Aqueducts\\Thermae",
+    "antemplate": "[Genre: <|>]",
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.40.0.dev0",
+    "use_cache": false,
+    "vocab_size": 32000,
+    "welcome": "## Warning: This model has a very heavy NSFW bias and is not suitable for use by minors!\n\nYou are currently running story-writing model `Erebus, version 3 (Mistral 7B).`\n\n This model is made by [Mr. Seeker](https://www.patreon.com/mrseeker) with help of ProudNoob and the KoboldAI team.\n\n### How to use this model\n\nErebus is designed to generate short stories and novels. Use the author's note to give it a certain genre to follow, use memory to give an overview of the story and use World Information to give specific details about the characters. To start off, give the AI an idea of what you are writing about by setting the scene. Give the AI around 10 sentences that make your story interesting to read. Introduce your character, describe the world, blow something up, or let the AI use its creative mind.",
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.18",
+        "bits": 6.5,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

6.5bpw/mergekit_config.yml

@@ -0,0 +1,12 @@
+dtype: float16
+merge_method: linear
+slices:
+- sources:
+  - layer_range: [0, 80]
+    model: f:\Aqueducts\Thermae
+    parameters:
+      weight: 0.5
+  - layer_range: [0, 80]
+    model: f:\Aqueducts\Circuses
+    parameters:
+      weight: 0.5

6.5bpw/model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 35422216192}, "weight_map": {"lm_head.weight": "model-00001-of-00004.safetensors", "model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors"}}

6.5bpw/output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a4b3abeb7de67d41c0b3ac6f0e95475516ca8601a04e4bbe47c366418f18fe
+size 8582646172

6.5bpw/output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9664f85a06a4d42e5d4f9671ac87dbebb3d7437151299568c706ce110771dfcd
+size 5959343928

6.5bpw/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

6.5bpw/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

6.5bpw/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

README.md

@@ -0,0 +1,9 @@
+---
+language:
+- en
+license: cc-by-nc-4.0
+base_model:
+  - upstage/SOLAR-10.7B-v1.0
+---
+
+EXL2 quants for Aqueducts 18B - https://huggingface.co/MarsupialAI/Aqueducts-18B