winglian commited on
Commit
5105c3a
1 Parent(s): c84c400

End of training

Browse files
README.md ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ base_model: HuggingFaceH4/mistral-7b-sft-beta
9
+ model-index:
10
+ - name: zephyr-deita-dpo-3ep-v3-r512-bsz8-alpha256
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ [<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)
18
+ <details><summary>See axolotl config</summary>
19
+
20
+ axolotl version: `0.3.0`
21
+ ```yaml
22
+ base_model: HuggingFaceH4/mistral-7b-sft-beta
23
+ model_type: MistralForCausalLM
24
+ tokenizer_type: LlamaTokenizer
25
+ is_mistral_derived_model: true
26
+
27
+ load_in_8bit: false
28
+ load_in_4bit: false
29
+ strict: false
30
+
31
+ rl: dpo
32
+ datasets:
33
+ - path: winglian/deita-nectar
34
+ split: train_dpo
35
+ type: zephyr.nectar
36
+ _test_datasets:
37
+ - path: winglian/deita-nectar
38
+ split: test_dpo
39
+ type: zephyr.nectar
40
+ dataset_prepared_path: last_run_prepared
41
+ val_set_size: 0.0
42
+ output_dir: ./zephyr-deita-dpo-3ep-v3-r512-bsz8-alpha256
43
+ save_total_limit: 3
44
+ hub_model_id: openaccess-ai-collective/dpo-zephyr-deita-nectar
45
+
46
+ adapter: lora
47
+ lora_model_dir:
48
+
49
+ sequence_len: 2048
50
+ sample_packing: false
51
+ pad_to_sequence_len: false
52
+
53
+ lora_r: 512
54
+ lora_alpha: 256
55
+ lora_dropout: 0.05
56
+ lora_target_linear: true
57
+ lora_modules_to_save:
58
+ lora_fan_in_fan_out:
59
+ lora_target_modules:
60
+ - gate_proj
61
+ - down_proj
62
+ - up_proj
63
+ - q_proj
64
+ - v_proj
65
+ - k_proj
66
+ - o_proj
67
+
68
+ wandb_project: dpo-zephyr-deita-nectar
69
+ wandb_entity: oaaic
70
+ wandb_watch:
71
+ wandb_run_id:
72
+ wandb_name: dpo-3ep-v3-r512-a256-bsz8-lr1.4e-5
73
+ wandb_log_model:
74
+
75
+ gradient_accumulation_steps: 1
76
+ micro_batch_size: 2
77
+ num_epochs: 3
78
+ optimizer: paged_adamw_8bit
79
+ adam_beta2: 0.95
80
+ adam_epsilion: 0.00001
81
+ lr_scheduler: linear
82
+ learning_rate: 1.414e-5
83
+
84
+ train_on_inputs: false
85
+ group_by_length: false
86
+ bf16: true
87
+ fp16: false
88
+ tf32: true
89
+
90
+ gradient_checkpointing: true
91
+ gradient_checkpoint_kwargs:
92
+ use_reentrant: true
93
+ early_stopping_patience:
94
+ resume_from_checkpoint:
95
+ local_rank:
96
+ logging_steps: 1
97
+ xformers_attention:
98
+ flash_attention: true
99
+
100
+ warmup_steps: 10
101
+ eval_steps:
102
+ eval_table_size:
103
+ eval_table_max_new_tokens: 128
104
+ save_steps: 45
105
+ debug:
106
+ deepspeed:
107
+ weight_decay: 0.1
108
+ fsdp:
109
+ fsdp_config:
110
+ special_tokens:
111
+ save_safetensors: true
112
+
113
+ dataloader_num_workers: 16
114
+ dataloader_pin_memory: true
115
+
116
+ ```
117
+
118
+ </details><br>
119
+
120
+ # zephyr-deita-dpo-3ep-v3-r512-bsz8-alpha256
121
+
122
+ 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.
123
+
124
+ ## Model description
125
+
126
+ More information needed
127
+
128
+ ## Intended uses & limitations
129
+
130
+ More information needed
131
+
132
+ ## Training and evaluation data
133
+
134
+ More information needed
135
+
136
+ ## Training procedure
137
+
138
+ ### Training hyperparameters
139
+
140
+ The following hyperparameters were used during training:
141
+ - learning_rate: 1.414e-05
142
+ - train_batch_size: 2
143
+ - eval_batch_size: 8
144
+ - seed: 42
145
+ - distributed_type: multi-GPU
146
+ - num_devices: 4
147
+ - total_train_batch_size: 8
148
+ - total_eval_batch_size: 32
149
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
150
+ - lr_scheduler_type: linear
151
+ - lr_scheduler_warmup_steps: 10
152
+ - training_steps: 3230
153
+
154
+ ### Training results
155
+
156
+
157
+
158
+ ### Framework versions
159
+
160
+ - PEFT 0.7.0
161
+ - Transformers 4.37.0.dev0
162
+ - Pytorch 2.0.1+cu118
163
+ - Datasets 2.16.1
164
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 256,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 512,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "o_proj",
23
+ "v_proj",
24
+ "up_proj",
25
+ "down_proj",
26
+ "k_proj",
27
+ "q_proj",
28
+ "gate_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c473b7a2e38cc0f4788b8a880424ab27457a363eb4dd76d5fcccca5cf63d570e
3
+ size 2684416656
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.37.0.dev0",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.37.0.dev0"
6
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f3dca0851d436fb35ca34da364810f6b098a2ba5714f8373d63744f65656ac
3
+ size 4998883808
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc5c22a83f787862112a4f7d2c4766c8ba200cf5e9e025acaf096dc43bf17fc9
3
+ size 4994690208
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a5d138d722c0f93f133200df53662d7730f868ca14949ffb61df1abfe20dc7e
3
+ size 4943343656
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e6ba151742033080b1b6142c9e148d7dd018f42e3eeedecd5c14a6449de074
3
+ size 2231527536
model.safetensors.index.json ADDED
@@ -0,0 +1,746 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17168351232
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
34
+ "model.layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
35
+ "model.layers.1.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
36
+ "model.layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
37
+ "model.layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
38
+ "model.layers.1.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
39
+ "model.layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
40
+ "model.layers.1.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
41
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
42
+ "model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
43
+ "model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
44
+ "model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
45
+ "model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
46
+ "model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
47
+ "model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
48
+ "model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
49
+ "model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
50
+ "model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
51
+ "model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
52
+ "model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
53
+ "model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
54
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.10.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.10.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.10.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.10.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.10.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.10.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.10.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.10.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.10.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.10.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.10.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.10.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.10.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.11.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.11.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.11.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.11.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.11.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.11.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.11.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.11.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.11.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.11.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.11.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.11.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.11.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.12.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.12.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.12.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.12.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.12.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.12.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.12.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.12.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.12.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.12.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.12.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.12.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.12.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.13.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.13.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.13.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.13.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.13.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.13.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.13.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.13.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.13.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.13.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.13.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
142
+ "model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
143
+ "model.layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
144
+ "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
145
+ "model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
146
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
147
+ "model.layers.14.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
148
+ "model.layers.14.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
149
+ "model.layers.14.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
150
+ "model.layers.14.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
151
+ "model.layers.14.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
152
+ "model.layers.14.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
153
+ "model.layers.14.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
154
+ "model.layers.14.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
155
+ "model.layers.14.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
156
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
157
+ "model.layers.14.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
158
+ "model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
159
+ "model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
161
+ "model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
162
+ "model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
163
+ "model.layers.14.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
164
+ "model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
165
+ "model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
166
+ "model.layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
167
+ "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
168
+ "model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
169
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
170
+ "model.layers.15.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
171
+ "model.layers.15.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
172
+ "model.layers.15.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
173
+ "model.layers.15.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
174
+ "model.layers.15.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
175
+ "model.layers.15.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
176
+ "model.layers.15.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
177
+ "model.layers.15.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
178
+ "model.layers.15.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
179
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
180
+ "model.layers.15.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
181
+ "model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
182
+ "model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
183
+ "model.layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
184
+ "model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
185
+ "model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
186
+ "model.layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
187
+ "model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
188
+ "model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
189
+ "model.layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
190
+ "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
191
+ "model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
192
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
193
+ "model.layers.16.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
194
+ "model.layers.16.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
195
+ "model.layers.16.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
196
+ "model.layers.16.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
197
+ "model.layers.16.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
198
+ "model.layers.16.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
199
+ "model.layers.16.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
200
+ "model.layers.16.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
201
+ "model.layers.16.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
202
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
203
+ "model.layers.16.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
204
+ "model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
205
+ "model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
206
+ "model.layers.16.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
207
+ "model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
208
+ "model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
209
+ "model.layers.16.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
210
+ "model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
211
+ "model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
212
+ "model.layers.16.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
213
+ "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
214
+ "model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
215
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
216
+ "model.layers.17.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
217
+ "model.layers.17.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
218
+ "model.layers.17.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
219
+ "model.layers.17.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
220
+ "model.layers.17.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
221
+ "model.layers.17.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
222
+ "model.layers.17.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
223
+ "model.layers.17.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
224
+ "model.layers.17.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
225
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
226
+ "model.layers.17.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
227
+ "model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
228
+ "model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
229
+ "model.layers.17.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
230
+ "model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
231
+ "model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
232
+ "model.layers.17.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
233
+ "model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
234
+ "model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
235
+ "model.layers.17.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
236
+ "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
237
+ "model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
238
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.18.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.18.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.18.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.18.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
243
+ "model.layers.18.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
244
+ "model.layers.18.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
245
+ "model.layers.18.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
246
+ "model.layers.18.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
247
+ "model.layers.18.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.18.self_attn.k_proj.base_layer.weight": "model-00002-of-00004.safetensors",
250
+ "model.layers.18.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
251
+ "model.layers.18.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
252
+ "model.layers.18.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
253
+ "model.layers.18.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
254
+ "model.layers.18.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
255
+ "model.layers.18.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
256
+ "model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
258
+ "model.layers.18.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
259
+ "model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
260
+ "model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
261
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
262
+ "model.layers.19.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
263
+ "model.layers.19.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
264
+ "model.layers.19.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
265
+ "model.layers.19.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
266
+ "model.layers.19.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
267
+ "model.layers.19.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
268
+ "model.layers.19.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
269
+ "model.layers.19.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
270
+ "model.layers.19.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
271
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
272
+ "model.layers.19.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
273
+ "model.layers.19.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
274
+ "model.layers.19.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
275
+ "model.layers.19.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
276
+ "model.layers.19.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
277
+ "model.layers.19.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
278
+ "model.layers.19.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
279
+ "model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
280
+ "model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
281
+ "model.layers.19.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
282
+ "model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
283
+ "model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
284
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
290
+ "model.layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
302
+ "model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
305
+ "model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
307
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
308
+ "model.layers.20.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
309
+ "model.layers.20.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
310
+ "model.layers.20.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
311
+ "model.layers.20.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
312
+ "model.layers.20.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
313
+ "model.layers.20.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
314
+ "model.layers.20.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
315
+ "model.layers.20.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
316
+ "model.layers.20.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
317
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
318
+ "model.layers.20.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
319
+ "model.layers.20.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
320
+ "model.layers.20.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
321
+ "model.layers.20.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
322
+ "model.layers.20.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
323
+ "model.layers.20.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
324
+ "model.layers.20.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
325
+ "model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
326
+ "model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
327
+ "model.layers.20.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
328
+ "model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
329
+ "model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
330
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
331
+ "model.layers.21.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
332
+ "model.layers.21.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
333
+ "model.layers.21.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
334
+ "model.layers.21.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
335
+ "model.layers.21.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
336
+ "model.layers.21.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
337
+ "model.layers.21.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
338
+ "model.layers.21.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
339
+ "model.layers.21.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
340
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
341
+ "model.layers.21.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
342
+ "model.layers.21.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
343
+ "model.layers.21.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
344
+ "model.layers.21.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
345
+ "model.layers.21.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
346
+ "model.layers.21.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
347
+ "model.layers.21.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
348
+ "model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
349
+ "model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
350
+ "model.layers.21.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
351
+ "model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
352
+ "model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
353
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
354
+ "model.layers.22.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
355
+ "model.layers.22.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
356
+ "model.layers.22.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
357
+ "model.layers.22.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
358
+ "model.layers.22.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
359
+ "model.layers.22.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
360
+ "model.layers.22.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
361
+ "model.layers.22.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
362
+ "model.layers.22.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
363
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
364
+ "model.layers.22.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
365
+ "model.layers.22.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
366
+ "model.layers.22.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
367
+ "model.layers.22.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
368
+ "model.layers.22.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
369
+ "model.layers.22.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
370
+ "model.layers.22.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
371
+ "model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
372
+ "model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
373
+ "model.layers.22.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
374
+ "model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
375
+ "model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
376
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
377
+ "model.layers.23.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
378
+ "model.layers.23.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
379
+ "model.layers.23.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
380
+ "model.layers.23.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
381
+ "model.layers.23.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
382
+ "model.layers.23.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
383
+ "model.layers.23.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
384
+ "model.layers.23.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
385
+ "model.layers.23.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
386
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
387
+ "model.layers.23.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
388
+ "model.layers.23.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
389
+ "model.layers.23.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
390
+ "model.layers.23.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
391
+ "model.layers.23.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
392
+ "model.layers.23.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
393
+ "model.layers.23.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
394
+ "model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
395
+ "model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
396
+ "model.layers.23.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
397
+ "model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
398
+ "model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
399
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
400
+ "model.layers.24.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
401
+ "model.layers.24.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
402
+ "model.layers.24.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
403
+ "model.layers.24.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
404
+ "model.layers.24.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
405
+ "model.layers.24.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
406
+ "model.layers.24.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
407
+ "model.layers.24.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
408
+ "model.layers.24.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
409
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
410
+ "model.layers.24.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
411
+ "model.layers.24.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
412
+ "model.layers.24.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
413
+ "model.layers.24.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
414
+ "model.layers.24.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
415
+ "model.layers.24.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
416
+ "model.layers.24.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
417
+ "model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
418
+ "model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
419
+ "model.layers.24.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
420
+ "model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
421
+ "model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
422
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
423
+ "model.layers.25.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
424
+ "model.layers.25.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
425
+ "model.layers.25.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
426
+ "model.layers.25.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
427
+ "model.layers.25.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
428
+ "model.layers.25.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
429
+ "model.layers.25.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
430
+ "model.layers.25.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
431
+ "model.layers.25.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
432
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
433
+ "model.layers.25.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
434
+ "model.layers.25.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
435
+ "model.layers.25.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
436
+ "model.layers.25.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
437
+ "model.layers.25.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
438
+ "model.layers.25.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
439
+ "model.layers.25.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
440
+ "model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
441
+ "model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
442
+ "model.layers.25.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
443
+ "model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
444
+ "model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
445
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
446
+ "model.layers.26.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
447
+ "model.layers.26.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
448
+ "model.layers.26.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
449
+ "model.layers.26.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
450
+ "model.layers.26.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
451
+ "model.layers.26.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
452
+ "model.layers.26.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
453
+ "model.layers.26.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
454
+ "model.layers.26.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
455
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
456
+ "model.layers.26.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
457
+ "model.layers.26.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
458
+ "model.layers.26.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
459
+ "model.layers.26.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
460
+ "model.layers.26.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
461
+ "model.layers.26.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
462
+ "model.layers.26.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
463
+ "model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
464
+ "model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
465
+ "model.layers.26.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
466
+ "model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
467
+ "model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
468
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
469
+ "model.layers.27.mlp.down_proj.base_layer.weight": "model-00003-of-00004.safetensors",
470
+ "model.layers.27.mlp.down_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
471
+ "model.layers.27.mlp.down_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
472
+ "model.layers.27.mlp.gate_proj.base_layer.weight": "model-00003-of-00004.safetensors",
473
+ "model.layers.27.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
474
+ "model.layers.27.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
475
+ "model.layers.27.mlp.up_proj.base_layer.weight": "model-00003-of-00004.safetensors",
476
+ "model.layers.27.mlp.up_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
477
+ "model.layers.27.mlp.up_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
478
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
479
+ "model.layers.27.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
480
+ "model.layers.27.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
481
+ "model.layers.27.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
482
+ "model.layers.27.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
483
+ "model.layers.27.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
484
+ "model.layers.27.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
485
+ "model.layers.27.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
486
+ "model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
487
+ "model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
488
+ "model.layers.27.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
489
+ "model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
490
+ "model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
491
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
492
+ "model.layers.28.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
493
+ "model.layers.28.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
494
+ "model.layers.28.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
495
+ "model.layers.28.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
496
+ "model.layers.28.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
497
+ "model.layers.28.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
498
+ "model.layers.28.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
499
+ "model.layers.28.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
500
+ "model.layers.28.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
501
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
502
+ "model.layers.28.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
503
+ "model.layers.28.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
504
+ "model.layers.28.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
505
+ "model.layers.28.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
506
+ "model.layers.28.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
507
+ "model.layers.28.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
508
+ "model.layers.28.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
509
+ "model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
510
+ "model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
511
+ "model.layers.28.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
512
+ "model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
513
+ "model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
514
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
515
+ "model.layers.29.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
516
+ "model.layers.29.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
517
+ "model.layers.29.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
518
+ "model.layers.29.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
519
+ "model.layers.29.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
520
+ "model.layers.29.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
521
+ "model.layers.29.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
522
+ "model.layers.29.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
523
+ "model.layers.29.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
524
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
525
+ "model.layers.29.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
526
+ "model.layers.29.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
527
+ "model.layers.29.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
528
+ "model.layers.29.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
529
+ "model.layers.29.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
530
+ "model.layers.29.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
531
+ "model.layers.29.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
532
+ "model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
533
+ "model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
534
+ "model.layers.29.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
535
+ "model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
536
+ "model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
537
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
538
+ "model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
539
+ "model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
540
+ "model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
541
+ "model.layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
542
+ "model.layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
543
+ "model.layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
544
+ "model.layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
545
+ "model.layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
546
+ "model.layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
547
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
548
+ "model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
549
+ "model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
550
+ "model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
551
+ "model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
552
+ "model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
553
+ "model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
554
+ "model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
555
+ "model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
556
+ "model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
557
+ "model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
558
+ "model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
559
+ "model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
560
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
561
+ "model.layers.30.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
562
+ "model.layers.30.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
563
+ "model.layers.30.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
564
+ "model.layers.30.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
565
+ "model.layers.30.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
566
+ "model.layers.30.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
567
+ "model.layers.30.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
568
+ "model.layers.30.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
569
+ "model.layers.30.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
570
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
571
+ "model.layers.30.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
572
+ "model.layers.30.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
573
+ "model.layers.30.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
574
+ "model.layers.30.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
575
+ "model.layers.30.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
576
+ "model.layers.30.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
577
+ "model.layers.30.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
578
+ "model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
579
+ "model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
580
+ "model.layers.30.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
581
+ "model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
582
+ "model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
583
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
584
+ "model.layers.31.mlp.down_proj.base_layer.weight": "model-00004-of-00004.safetensors",
585
+ "model.layers.31.mlp.down_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
586
+ "model.layers.31.mlp.down_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
587
+ "model.layers.31.mlp.gate_proj.base_layer.weight": "model-00004-of-00004.safetensors",
588
+ "model.layers.31.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
589
+ "model.layers.31.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
590
+ "model.layers.31.mlp.up_proj.base_layer.weight": "model-00004-of-00004.safetensors",
591
+ "model.layers.31.mlp.up_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
592
+ "model.layers.31.mlp.up_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
593
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
594
+ "model.layers.31.self_attn.k_proj.base_layer.weight": "model-00004-of-00004.safetensors",
595
+ "model.layers.31.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
596
+ "model.layers.31.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
597
+ "model.layers.31.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
598
+ "model.layers.31.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
599
+ "model.layers.31.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
600
+ "model.layers.31.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
601
+ "model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
602
+ "model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
603
+ "model.layers.31.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
604
+ "model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
605
+ "model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
606
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
607
+ "model.layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
608
+ "model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
609
+ "model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
610
+ "model.layers.4.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
611
+ "model.layers.4.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
612
+ "model.layers.4.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
613
+ "model.layers.4.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
614
+ "model.layers.4.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
615
+ "model.layers.4.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
616
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
617
+ "model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
618
+ "model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
619
+ "model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
620
+ "model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
621
+ "model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
622
+ "model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
623
+ "model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
624
+ "model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
625
+ "model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
626
+ "model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
627
+ "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
628
+ "model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
629
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
630
+ "model.layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
631
+ "model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
632
+ "model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
633
+ "model.layers.5.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
634
+ "model.layers.5.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
635
+ "model.layers.5.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
636
+ "model.layers.5.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
637
+ "model.layers.5.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
638
+ "model.layers.5.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
639
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
640
+ "model.layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
641
+ "model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
642
+ "model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
643
+ "model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
644
+ "model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
645
+ "model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
646
+ "model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
647
+ "model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
648
+ "model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
649
+ "model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
650
+ "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
651
+ "model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
652
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
653
+ "model.layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
654
+ "model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
655
+ "model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
656
+ "model.layers.6.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
657
+ "model.layers.6.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
658
+ "model.layers.6.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
659
+ "model.layers.6.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
660
+ "model.layers.6.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
661
+ "model.layers.6.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
662
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
663
+ "model.layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
664
+ "model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
665
+ "model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
666
+ "model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
667
+ "model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
668
+ "model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
669
+ "model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
670
+ "model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
671
+ "model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
672
+ "model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
673
+ "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
674
+ "model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
675
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
676
+ "model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
677
+ "model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
678
+ "model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
679
+ "model.layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
680
+ "model.layers.7.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
681
+ "model.layers.7.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
682
+ "model.layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
683
+ "model.layers.7.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
684
+ "model.layers.7.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
685
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
686
+ "model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
687
+ "model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
688
+ "model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
689
+ "model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
690
+ "model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
691
+ "model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
692
+ "model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
693
+ "model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
694
+ "model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
695
+ "model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
696
+ "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
697
+ "model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
698
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
699
+ "model.layers.8.mlp.down_proj.base_layer.weight": "model-00001-of-00004.safetensors",
700
+ "model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
701
+ "model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
702
+ "model.layers.8.mlp.gate_proj.base_layer.weight": "model-00001-of-00004.safetensors",
703
+ "model.layers.8.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
704
+ "model.layers.8.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
705
+ "model.layers.8.mlp.up_proj.base_layer.weight": "model-00001-of-00004.safetensors",
706
+ "model.layers.8.mlp.up_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
707
+ "model.layers.8.mlp.up_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
708
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
709
+ "model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
710
+ "model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
711
+ "model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
712
+ "model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
713
+ "model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
714
+ "model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
715
+ "model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
716
+ "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
717
+ "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
718
+ "model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
719
+ "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
720
+ "model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
721
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
722
+ "model.layers.9.mlp.down_proj.base_layer.weight": "model-00002-of-00004.safetensors",
723
+ "model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
724
+ "model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
725
+ "model.layers.9.mlp.gate_proj.base_layer.weight": "model-00002-of-00004.safetensors",
726
+ "model.layers.9.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
727
+ "model.layers.9.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
728
+ "model.layers.9.mlp.up_proj.base_layer.weight": "model-00002-of-00004.safetensors",
729
+ "model.layers.9.mlp.up_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
730
+ "model.layers.9.mlp.up_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
731
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
732
+ "model.layers.9.self_attn.k_proj.base_layer.weight": "model-00001-of-00004.safetensors",
733
+ "model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
734
+ "model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
735
+ "model.layers.9.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
736
+ "model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
737
+ "model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
738
+ "model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
739
+ "model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
740
+ "model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
741
+ "model.layers.9.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
742
+ "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
743
+ "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
744
+ "model.norm.weight": "model-00004-of-00004.safetensors"
745
+ }
746
+ }
runs/Jan16_01-47-58_b5637b3f66b9/events.out.tfevents.1705369791.b5637b3f66b9.150766.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3684380a515feac2322f16113d84a7b6acfa440d85410d266d8855946ec9854a
3
+ size 32540
runs/Jan16_01-54-42_b5637b3f66b9/events.out.tfevents.1705370108.b5637b3f66b9.155498.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62b830a76a620d6ae217348665aa62439a88d3440f3c5d4e970c15b68a7309a9
3
+ size 2051282
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "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 %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "</s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "truncation_side": "left",
46
+ "trust_remote_code": false,
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": true,
49
+ "use_fast": true
50
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0507a7748569247ae51eea6beffac59a8ca6d69b91016c7ec53390bb73e12b0f
3
+ size 4347