Upload folder using huggingface_hub

README.md

@@ -0,0 +1,43 @@
+---
+base_model:
+- mistralai/Mistral-7B-Instruct-v0.3
+library_name: transformers
+tags:
+- mergekit
+license: apache-2.0
+language:
+- en
+---
+# mistral-7b-instruct-v0.3-depth-upscaling
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/643eab4f05a395e2b1c727e3/elcrExK_Q5MQjcdAjYi9V.png)
+
+This is an attempt at depth upscaling , Based on the paper [SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling](https://arxiv.org/abs/2312.15166), which is a technique designed to efficiently scale large language models. The process begins with structural depthwise scaling which may initially reduce performance, but this is rapidly restored during a crucial continued pretraining phase. This phase optimizes the expanded model's parameters to the new depth configuration, significantly enhancing performance.
+
+It's important to note that this represents only the initial phase of the model's development. The next critical steps involve fine-tuning,
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method. The first 24 layers of one copy of the model are stitched to the last 24 layers of another copy, resulting in a total of 48 layers with 10.7B parameters.
+
+### Models Merged
+
+The following models were included in the merge:
+* [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) merged with itself.
+
+### Configuration
+
+The following configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+    - model: mistralai/Mistral-7B-Instruct-v0.3
+      layer_range: [0, 24]
+  - sources:
+    - model: mistralai/Mistral-7B-Instruct-v0.3
+      layer_range: [8, 32]
+merge_method: passthrough
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,37 @@
+{
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+    "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": 48,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.38.2",
+    "use_cache": true,
+    "vocab_size": 32768,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.21",
+        "bits": 3.75,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+slices:
+  - sources:
+    - model: mistralai/Mistral-7B-Instruct-v0.3
+      layer_range: [0, 24]
+  - sources:
+    - model: mistralai/Mistral-7B-Instruct-v0.3
+      layer_range: [8, 32]
+merge_method: passthrough
+dtype: bfloat16

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 21475631104}, "weight_map": {"lm_head.weight": "model-00001-of-00005.safetensors", "model.embed_tokens.weight": "model-00001-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.41.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.47.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.norm.weight": "model-00005-of-00005.safetensors"}}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2cef612345538baba35d151eaa3d2ea1fa2c971046ca80670bceb80f8396c4c
+size 5278992924

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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404