End of training

README.md

@@ -0,0 +1,164 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: HuggingFaceH4/mistral-7b-sft-beta
+model-index:
+- name: zephyr-deita-dpo-3ep-v3-r512-bsz8-alpha256
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.3.0`
+```yaml
+base_model: HuggingFaceH4/mistral-7b-sft-beta
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+rl: dpo
+datasets:
+  - path: winglian/deita-nectar
+    split: train_dpo
+    type: zephyr.nectar
+_test_datasets:
+  - path: winglian/deita-nectar
+    split: test_dpo
+    type: zephyr.nectar
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.0
+output_dir: ./zephyr-deita-dpo-3ep-v3-r512-bsz8-alpha256
+save_total_limit: 3
+hub_model_id: openaccess-ai-collective/dpo-zephyr-deita-nectar
+
+adapter: lora
+lora_model_dir:
+
+sequence_len: 2048
+sample_packing: false
+pad_to_sequence_len: false
+
+lora_r: 512
+lora_alpha: 256
+lora_dropout: 0.05
+lora_target_linear: true
+lora_modules_to_save:
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+wandb_project: dpo-zephyr-deita-nectar
+wandb_entity: oaaic
+wandb_watch:
+wandb_run_id:
+wandb_name: dpo-3ep-v3-r512-a256-bsz8-lr1.4e-5
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 2
+num_epochs: 3
+optimizer: paged_adamw_8bit
+adam_beta2: 0.95
+adam_epsilion: 0.00001
+lr_scheduler: linear
+learning_rate: 1.414e-5
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: true
+
+gradient_checkpointing: true
+gradient_checkpoint_kwargs:
+  use_reentrant: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+eval_steps:
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps: 45
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+special_tokens:
+save_safetensors: true
+
+dataloader_num_workers: 16
+dataloader_pin_memory: true
+
+```
+
+</details><br>
+
+# zephyr-deita-dpo-3ep-v3-r512-bsz8-alpha256
+
+This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None 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: 1.414e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 8
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- training_steps: 3230
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.0
+- Transformers 4.37.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 512,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c473b7a2e38cc0f4788b8a880424ab27457a363eb4dd76d5fcccca5cf63d570e
+size 2684416656

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f3dca0851d436fb35ca34da364810f6b098a2ba5714f8373d63744f65656ac
+size 4998883808

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc5c22a83f787862112a4f7d2c4766c8ba200cf5e9e025acaf096dc43bf17fc9
+size 4994690208

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5d138d722c0f93f133200df53662d7730f868ca14949ffb61df1abfe20dc7e
+size 4943343656

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e6ba151742033080b1b6142c9e148d7dd018f42e3eeedecd5c14a6449de074
+size 2231527536

model.safetensors.index.json

@@ -0,0 +1,746 @@
+{
+  "metadata": {
+    "total_size": 17168351232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

runs/Jan16_01-47-58_b5637b3f66b9/events.out.tfevents.1705369791.b5637b3f66b9.150766.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3684380a515feac2322f16113d84a7b6acfa440d85410d266d8855946ec9854a
+size 32540

runs/Jan16_01-54-42_b5637b3f66b9/events.out.tfevents.1705370108.b5637b3f66b9.155498.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b830a76a620d6ae217348665aa62439a88d3440f3c5d4e970c15b68a7309a9
+size 2051282

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0507a7748569247ae51eea6beffac59a8ca6d69b91016c7ec53390bb73e12b0f
+size 4347