Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* 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
+maiden.png filter=lfs diff=lfs merge=lfs -text
+maidenq.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,55 @@
+---
+base_model:
+- TeeZee/BigMaid-20B-v1.0
+- TeeZee/DarkForest-20B-v2.0
+- athirdpath/Harmonia-20B
+library_name: transformers
+tags:
+- mergekit
+- merge
+- not-for-all-audiences
+---
+
+![](maidenq.png)
+
+# Maiden-Unquirked-20B
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+
+See Below
+
+### Merge Method
+
+This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [TeeZee/DarkForest-20B-v2.0](https://huggingface.co/TeeZee/DarkForest-20B-v2.0) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [TeeZee/BigMaid-20B-v1.0](https://huggingface.co/TeeZee/BigMaid-20B-v1.0)
+* [athirdpath/Harmonia-20B](https://huggingface.co/athirdpath/Harmonia-20B)
+* [TeeZee/DarkForest-20B-v2.0](https://huggingface.co/TeeZee/DarkForest-20B-v2.0)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: TeeZee/DarkForest-20B-v2.0
+  - model: athirdpath/Harmonia-20B
+    parameters:
+      weight: 0.5
+      density: 1.0
+  - model: TeeZee/BigMaid-20B-v1.0
+    parameters:
+      weight: 0.5
+      density: 1.0
+merge_method: dare_ties
+base_model: TeeZee/DarkForest-20B-v2.0
+parameters:
+  int8_mask: true
+dtype: bfloat16
+name: maiden_unquirked
+```

config.json

@@ -0,0 +1,41 @@
+{
+    "_name_or_path": "TeeZee/DarkForest-20B-v2.0",
+    "antemplate": "[Genre: <|>]",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 13824,
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 62,
+    "num_key_value_heads": 40,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.38.2",
+    "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 (LLaMA2 13B).`\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": "0.1.4",
+        "bits": 3.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+models:
+  - model: TeeZee/DarkForest-20B-v2.0
+  - model: athirdpath/Harmonia-20B
+    parameters:
+      weight: 0.5
+      density: 1.0
+  - model: TeeZee/BigMaid-20B-v1.0
+    parameters:
+      weight: 0.5
+      density: 1.0
+merge_method: dare_ties
+base_model: TeeZee/DarkForest-20B-v2.0
+parameters:
+  int8_mask: true
+dtype: bfloat16
+name: maiden_unquirked

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00021.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00021.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00021.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00021.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00021.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00021.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00021.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00021.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00021.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00021.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00021.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00021.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00021.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00021.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00021.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00021.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00021.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00021.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00021.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00021.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00021.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00021.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00021.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00021.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00021.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00021.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00021.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00021.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00021.safetensors", "model.embed_tokens.weight": "model-00003-of-00021.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00021.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00021.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00021.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00021.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00021.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00021.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00021.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00021.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00021.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00021.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00021.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00021.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00021.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00021.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00021.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00021.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00021.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00021.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00021.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00021.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00021.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00021.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00021.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00021.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00021.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00021.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00021.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00021.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00021.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00021.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00021.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00021.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00021.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00021.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00021.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00021.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00021.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00021.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00021.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00021.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00021.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00021.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00021.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00021.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00021.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00021.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00021.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00021.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00021.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00021.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00021.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00021.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00021.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00021.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00021.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00021.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00021.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00021.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00021.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00021.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00021.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00021.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00021.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00021.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00021.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00021.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00021.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00021.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00021.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00021.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00021.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00021.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00021.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00021.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00021.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00021.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00021.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00021.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00021.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00021.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00021.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00021.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00021.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00021.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00021.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00021.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00021.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00021.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00021.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00007-of-00021.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00021.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00021.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00021.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00021.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00021.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00007-of-00021.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00021.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00008-of-00021.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00021.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00021.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00021.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00021.safetensors", "model.layers.13.input_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00008-of-00021.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00021.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00008-of-00021.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00021.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00021.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00021.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00021.safetensors", "model.layers.12.input_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00008-of-00021.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00008-of-00021.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00008-of-00021.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00021.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00021.safetensors", "model.layers.11.input_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00008-of-00021.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00021.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00008-of-00021.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00021.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00021.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00021.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00021.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00021.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00021.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00021.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00021.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00021.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00021.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00021.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00021.safetensors", "model.layers.8.input_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00009-of-00021.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00009-of-00021.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00009-of-00021.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00021.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00021.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00021.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00021.safetensors", "model.layers.7.input_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00009-of-00021.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00021.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00009-of-00021.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00021.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00021.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00021.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00021.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00021.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00021.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00021.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00021.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00021.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00021.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00021.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00021.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00021.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00021.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00021.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00021.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00021.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00021.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00021.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00021.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00021.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00021.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00021.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00021.safetensors", "model.layers.41.input_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00011-of-00021.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00011-of-00021.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00011-of-00021.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00021.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00011-of-00021.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00021.safetensors", "model.layers.40.input_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00011-of-00021.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00021.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00011-of-00021.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00021.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00021.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00021.safetensors", "model.layers.39.input_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00021.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00021.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00011-of-00021.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00021.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00021.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00021.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00021.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.38.input_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00021.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00021.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00012-of-00021.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00021.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00021.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00021.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00021.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00021.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00021.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00021.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00021.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00021.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00021.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00021.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00021.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00021.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00021.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00021.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00021.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00021.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00013-of-00021.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00021.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00013-of-00021.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00021.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00021.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00021.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.34.input_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00013-of-00021.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00021.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00013-of-00021.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00021.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00021.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00021.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00021.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00021.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00013-of-00021.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00021.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00021.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00021.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00021.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00021.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00014-of-00021.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00021.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00014-of-00021.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00021.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00021.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00021.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00021.safetensors", "model.layers.31.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00014-of-00021.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00021.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00014-of-00021.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00021.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00021.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00021.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00021.safetensors", "model.layers.30.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00014-of-00021.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00021.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00014-of-00021.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00021.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00021.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00021.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00021.safetensors", "model.layers.29.input_layernorm.weight": "model-00014-of-00021.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00015-of-00021.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00021.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00015-of-00021.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00021.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00021.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00021.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00021.safetensors", "model.layers.28.input_layernorm.weight": "model-00015-of-00021.safetensors", "lm_head.weight": "model-00015-of-00021.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00015-of-00021.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00015-of-00021.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00015-of-00021.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00015-of-00021.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00015-of-00021.safetensors", "model.layers.61.input_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00015-of-00021.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00015-of-00021.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00015-of-00021.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00015-of-00021.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00015-of-00021.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00016-of-00021.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00016-of-00021.safetensors", "model.layers.60.input_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00016-of-00021.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00016-of-00021.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00016-of-00021.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00016-of-00021.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00016-of-00021.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00016-of-00021.safetensors", "model.layers.59.input_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00016-of-00021.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00016-of-00021.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00016-of-00021.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00016-of-00021.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00016-of-00021.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00016-of-00021.safetensors", "model.layers.58.input_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00016-of-00021.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00016-of-00021.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00016-of-00021.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00016-of-00021.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00016-of-00021.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00016-of-00021.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00017-of-00021.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00017-of-00021.safetensors", "model.layers.57.input_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00017-of-00021.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00017-of-00021.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00017-of-00021.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00017-of-00021.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00017-of-00021.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00017-of-00021.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00017-of-00021.safetensors", "model.layers.56.input_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00017-of-00021.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00017-of-00021.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00017-of-00021.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00017-of-00021.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00017-of-00021.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00017-of-00021.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00017-of-00021.safetensors", "model.layers.55.input_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00017-of-00021.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00017-of-00021.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00017-of-00021.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00017-of-00021.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00017-of-00021.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00017-of-00021.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00017-of-00021.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.54.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00018-of-00021.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00018-of-00021.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00018-of-00021.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.53.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00018-of-00021.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00018-of-00021.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00018-of-00021.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.52.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00018-of-00021.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00021.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00018-of-00021.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00018-of-00021.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00018-of-00021.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00018-of-00021.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00018-of-00021.safetensors", "model.layers.51.input_layernorm.weight": "model-00018-of-00021.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00019-of-00021.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00021.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00019-of-00021.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00021.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00021.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00021.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00021.safetensors", "model.layers.50.input_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00019-of-00021.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00021.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00019-of-00021.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00021.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00019-of-00021.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00019-of-00021.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00019-of-00021.safetensors", "model.layers.49.input_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00019-of-00021.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00019-of-00021.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00019-of-00021.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00019-of-00021.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00019-of-00021.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00019-of-00021.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00019-of-00021.safetensors", "model.layers.48.input_layernorm.weight": "model-00019-of-00021.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00020-of-00021.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00021.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00020-of-00021.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00021.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00021.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.47.input_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00020-of-00021.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00020-of-00021.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00020-of-00021.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00021.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.46.input_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00020-of-00021.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00020-of-00021.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00020-of-00021.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00021.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00020-of-00021.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.45.input_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00020-of-00021.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00021-of-00021.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00021-of-00021.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00021-of-00021.safetensors", "model.layers.44.input_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00021-of-00021.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00021-of-00021.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00021-of-00021.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00021-of-00021.safetensors", "model.layers.43.input_layernorm.weight": "model-00021-of-00021.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00021-of-00021.safetensors", "model.norm.weight": "model-00021-of-00021.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00021-of-00021.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00021-of-00021.safetensors"}}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50baafd38db7f742198e1fd4787af80d134237014b7547e4030e3489c80e49c1
+size 7831965052

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
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}