初始化项目，由ModelHub XC社区提供模型

Model: neuralmagic/Nous-Hermes-2-SOLAR-10.7B-pruned2.4
Source: Original Platform

.gitattributes

@@ -0,0 +1,38 @@
+*.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
+pytorch_model-00001-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00003.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,86 @@
+---
+base_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
+inference: True
+model_type: Llama
+tags:
+- nm-vllm
+- sparse
+---
+## Nous-Hermes-2-SOLAR-10.7B-pruned2.4
+This repo contains model files for [Nous-Hermes-2-SOLAR-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B) optimized for [NM-vLLM](https://github.com/neuralmagic/nm-vllm), a high-throughput serving engine for compressed LLMs.
+
+This model was pruned with [SparseGPT](https://arxiv.org/abs/2301.00774), using [SparseML](https://github.com/neuralmagic/sparseml).
+
+## Inference
+Install [NM-vLLM](https://github.com/neuralmagic/nm-vllm) for fast inference and low memory-usage: 
+```bash
+pip install nm-vllm[sparse]
+```
+Run in a Python pipeline for local inference:
+```python
+from vllm import LLM, SamplingParams
+
+model = LLM("nm-testing/Nous-Hermes-2-SOLAR-10.7B-pruned2.4", sparsity="semi_structured_sparse_w16a16")
+prompt = "How to make banana bread?"
+formatted_prompt =  f"<|im_start|>User:{prompt}\n<|im_start|>assistant:\n"
+
+sampling_params = SamplingParams(max_tokens=100)
+outputs = model.generate(formatted_prompt, sampling_params=sampling_params)
+print(outputs[0].outputs[0].text)
+"""
+To make banana bread, you will need to follow these steps:
+
+1. Gather the ingredients needed for the recipe: flour, sugar, eggs, baking powder, and banana bread.
+2. Preparing the bread by kneading the flour, butter, and sugar in a bowl until it becomes soft.
+3. Then, knead the bread with the flour eggs and sugar then bake them in a microwave oven.
+4. Once done baking a
+"""
+```
+
+## Prompt template
+
+```
+### User:
+{prompt}
+### Assistant:"
+```
+
+## Sparsification
+For details on how this model was sparsified, see the `recipe.yaml` in this repo and follow the instructions below.
+
+Install [SparseML](https://github.com/neuralmagic/sparseml):
+```bash
+git clone https://github.com/neuralmagic/sparseml
+pip install -e "sparseml[transformers]"
+```
+
+Replace the recipe as you like and run this one-shot compression script to apply SparseGPT:
+```python
+import sparseml.transformers
+
+original_model_name = "NousResearch/Nous-Hermes-2-SOLAR-10.7B"
+calibration_dataset = "open_platypus"
+output_directory = "output/"
+
+recipe = """
+test_stage:
+  obcq_modifiers:
+    SparseGPTModifier:
+      sparsity: 0.5
+      sequential_update: true
+      mask_structure: '2:4'
+      targets: ['re:model.layers.\d*$']
+"""
+
+# Apply SparseGPT to the model
+sparseml.transformers.oneshot(
+    model=original_model_name,
+    dataset=calibration_dataset,
+    recipe=recipe,
+    output_dir=output_directory,
+)
+```
+
+## Slack
+
+For further support, and discussions on these models and AI in general, join [Neural Magic's Slack Community](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ)

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "NousResearch/Nous-Hermes-2-SOLAR-10.7B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "1.7.0.20240130",
+  "use_cache": false,
+  "vocab_size": 32002
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "1.7.0.20240130",
+  "use_cache": false
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed2cb596fad74ccb18aa636354690bdd2992d478e7bf068d059ab5b238ebd11
+size 9943047731

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d76fd6feb9ce88e12f8031e01503a3570c61a37472aee40b572c9816ebf0f40
+size 9999672004

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071f3f746b784749b751dd5f17363f481fad153e7ff12f58316d0307564c3167
+size 1520518398

pytorch_model.bin.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 21463080960
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

recipe.yaml

@@ -0,0 +1,10 @@
+test_stage:
+  obcq_modifiers:
+    SparseGPTModifier:
+      sparsity: 0.5
+      block_size: 128
+      sequential_update: true
+      quantize: false
+      percdamp: 0.01
+      mask_structure: '2:4'
+      targets: ['re:model.layers.\d*$']

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_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_config.json

@@ -0,0 +1,61 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}