oakela/finetuned_starcoder2_600steps

README.md

@@ -0,0 +1,59 @@
+---
+license: bigcode-openrail-m
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: bigcode/starcoder2-3b
+model-index:
+- name: finetune_starcoder2_600steps
+  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. -->
+
+# finetune_starcoder2_600steps
+
+This model is a fine-tuned version of [bigcode/starcoder2-3b](https://huggingface.co/bigcode/starcoder2-3b) on an unknown dataset.
+
+## 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 0
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- training_steps: 600
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder2-3b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030da7312a82483c8a688d4037d8b70eb880793e00bcae4b7c8c7511635a10da
+size 18218008

final_checkpoint/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "bigcode/starcoder2-3b",
+  "architectures": [
+    "Starcoder2ForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "embedding_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 3072,
+  "initializer_range": 0.018042,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 16384,
+  "mlp_type": "default",
+  "model_type": "starcoder2",
+  "norm_epsilon": 1e-05,
+  "norm_type": "layer_norm",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 2,
+  "residual_dropout": 0.1,
+  "rope_theta": 999999.4420358813,
+  "sliding_window": 4096,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 49152
+}

final_checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.39.0.dev0"
+}

final_checkpoint/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c85a8f7c61fce37a0c1672a7ca9211a4956dbc6ffa639105b7115d27b918cbf9
+size 4916180040

final_checkpoint/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f3dce8f8f44b80bcfe2ab6e47e8413bdb71879a6a48d556e2b43624ac67ccf
+size 4998826856

final_checkpoint/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05945e7978f2e0cb243d2f56ac3d415f6011c8f6fb399c239816f62f9a267b2e
+size 2224751784

final_checkpoint/model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 12139671552
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.base_layer.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.base_layer.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.base_layer.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.norm.bias": "model-00003-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

runs/Mar14_08-29-03_b422eb012e4e/events.out.tfevents.1710404944.b422eb012e4e.505.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ae89e28b2ce6336094748f2fe653c55152093086d6d0947de4ce221f8488b9
+size 17682

special_tokens_map.json

@@ -0,0 +1,64 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,357 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fbd9af04462b968aabb464cd27148e5c6e18b656a3181124f7a215355de6589
+size 4920