Model save

README.md

@@ -0,0 +1,69 @@
+---
+license: llama2
+base_model: codellama/CodeLlama-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: sqlcoder_7b_fullft_ds7_linear
+ 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. -->
+
+# sqlcoder_7b_fullft_ds7_linear
+
+This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3517
+- Sql Exact Match String: 0
+- Tokens Match Avg: 0.9014
+- First Index Mismatch Avg: 2.2356
+- Mean Mismatch I Diff Avg: 12.5313
+- Count Mismatch I Diff Avg: 6.2756
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 600
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Sql Exact Match String | Tokens Match Avg | First Index Mismatch Avg | Mean Mismatch I Diff Avg | Count Mismatch I Diff Avg |
+|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:----------------:|:------------------------:|:------------------------:|:-------------------------:|
+| 0.14 | 0.1 | 100 | 0.3510 | 0 | 0.8940 | 2.0844 | 11.4371 | 6.88 |
+| 0.1083 | 0.2 | 200 | 0.3677 | 0 | 0.8930 | 2.1733 | 11.3445 | 6.6044 |
+| 0.0912 | 0.3 | 300 | 0.3710 | 0 | 0.8953 | 2.2444 | 12.0020 | 6.44 |
+| 0.0699 | 0.4 | 400 | 0.3598 | 0 | 0.8996 | 2.1778 | 12.3582 | 6.3289 |
+| 0.0619 | 0.5 | 500 | 0.3516 | 0 | 0.9010 | 2.2489 | 12.6065 | 6.2756 |
+| 0.0766 | 0.6 | 600 | 0.3517 | 0 | 0.9014 | 2.2356 | 12.5313 | 6.2756 |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

generation_config.json

@@ -0,0 +1,6 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "transformers_version": "4.37.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d50a7eb3468bc529d58b6531633f1f38cf9cb771251ac9eac20efb569fb0ecb1
+size 4939116424

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9044eaedda9f64f18b458aa4adebff5bdeaa39931d43f5168c015d0d24be65
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2479750d695d24950273a27c8c02d3bd92e3ffbec816a2ce9ab0abcb364685c
+size 3590619888

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+ "metadata": {
+ "total_size": 13477093376
+ },
+ "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-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-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-00001-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-00001-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-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-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-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-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-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-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"
+ }
+}