End of training

README.md

@@ -0,0 +1,101 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: Mistral_Sparse_refined_web_relu_2024-02-16
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Mistral_Sparse_refined_web_relu_2024-02-16
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4640
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 0
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- total_eval_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 8.7883        | 0.0   | 25   | 8.7175          |
+| 8.1895        | 0.01  | 50   | 8.1790          |
+| 7.7646        | 0.01  | 75   | 7.8165          |
+| 7.5412        | 0.02  | 100  | 7.6103          |
+| 7.2131        | 0.02  | 125  | 7.1825          |
+| 4.8603        | 0.02  | 150  | 4.8039          |
+| 3.7952        | 0.03  | 175  | 3.8330          |
+| 3.2884        | 0.03  | 200  | 3.4432          |
+| 3.106         | 0.04  | 225  | 3.2520          |
+| 3.0004        | 0.04  | 250  | 3.1245          |
+| 2.8648        | 0.04  | 275  | 3.0460          |
+| 2.8349        | 0.05  | 300  | 2.9954          |
+| 2.7982        | 0.05  | 325  | 2.9562          |
+| 2.6109        | 0.06  | 350  | 2.9206          |
+| 2.7517        | 0.06  | 375  | 2.8975          |
+| 2.7817        | 0.06  | 400  | 2.8770          |
+| 2.7346        | 0.07  | 425  | 2.8580          |
+| 2.7019        | 0.07  | 450  | 2.8443          |
+| 2.5852        | 0.08  | 475  | 2.8288          |
+| 2.6452        | 0.08  | 500  | 2.8196          |
+| 2.7203        | 0.08  | 525  | 2.8109          |
+| 2.627         | 0.09  | 550  | 2.8013          |
+| 2.7272        | 0.09  | 575  | 2.7899          |
+| 2.5443        | 0.1   | 600  | 2.7826          |
+| 2.6178        | 0.1   | 625  | 2.7782          |
+| 2.656         | 0.1   | 650  | 2.7680          |
+| 2.676         | 0.11  | 675  | 2.7593          |
+| 2.6061        | 0.11  | 700  | 2.7539          |
+| 2.6263        | 0.12  | 725  | 2.7511          |
+| 2.5305        | 0.12  | 750  | 2.7474          |
+| 2.5344        | 0.12  | 775  | 2.7408          |
+| 2.655         | 0.13  | 800  | 2.7377          |
+| 2.6113        | 0.13  | 825  | 2.7332          |
+| 2.5946        | 0.14  | 850  | 2.7296          |
+| 2.4564        | 0.14  | 875  | 2.7270          |
+| 2.5591        | 0.14  | 900  | 2.7272          |
+| 2.4965        | 0.15  | 925  | 2.7205          |
+| 2.6231        | 0.15  | 950  | 2.7195          |
+| 2.5395        | 0.16  | 975  | 2.7162          |
+| 2.5741        | 0.16  | 1000 | 2.7145          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/scr/jay/ckpt/Mistral_Sparse_refined_web_relu",
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
   "architectures": [
     "SparseMistralforCausalLM"
   ],
@@ -60,7 +60,7 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
   "use_cache": false,
-  "use_relu": false,
+  "use_relu": true,
   "use_sparse_model": true,
   "use_sparse_predictor": false,
   "use_sparse_regularization": false,

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bceb9b2228cc82955030a53af407954988bdf719111367111db25f1c34ac24e0
-size 4943162336
+oid sha256:d394382fa4b8dd6d80aad207d908a1d97c4d2bcb79759386854c2522c6a88c77
+size 4943163992

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a3cff762a68c1463132378504b45973ef2ae74c3ed6b1f9fd5368ffedbfd043
-size 4999819336
+oid sha256:bcad5e87b4e0757b20707645a28622da7778e81f508bfd3be2c71be6b8925ffd
+size 4999821144

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e17cefee75d7925a2ec7a924f4889873db98c941a432ed76117644495cf099
-size 4540516344
+oid sha256:3aab14818953250fc7aeedb149239e67219f94481273e5985d37ab42ca63f4af
+size 4540517840

model.safetensors.index.json

@@ -3,296 +3,296 @@
     "total_size": 14483464192
   },
   "weight_map": {
-    "lm_head.weight": "model-00003-of-00003.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.norm.weight": "model-00003-of-00003.safetensors"
+    "base_model.model.lm_head.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "base_model.model.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "base_model.model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "base_model.model.model.norm.weight": "model-00003-of-00003.safetensors"
   }
 }