Hugging Face's logo

noeloco
/
modeltest1-dpo

PEFT
PyTorch
TensorBoard
Safetensors
llama
axolotl
dpo
trl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
noeloco commited on
Commit
0e5e4cb
•
1 Parent(s): 8cb8214

Training in progress, step 148

Browse files
Files changed (14) hide show
  1. adapter_config.json +34 -0
  2. adapter_model.safetensors +3 -0
  3. config.json +43 -0
  4. generation_config.json +7 -0
  5. pytorch_model-00001-of-00003.bin +3 -0
  6. pytorch_model-00002-of-00003.bin +3 -0
  7. pytorch_model-00003-of-00003.bin +3 -0
  8. pytorch_model.bin.index.json +746 -0
  9. runs/Apr29_13-09-35_4da20d8147fc/events.out.tfevents.1714396178.4da20d8147fc.11908.0 +3 -0
  10. runs/Apr29_13-13-12_4da20d8147fc/events.out.tfevents.1714396394.4da20d8147fc.14040.0 +3 -0
  11. special_tokens_map.json +30 -0
  12. tokenizer.model +3 -0
  13. tokenizer_config.json +86 -0
  14. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 8,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "gate_proj",
25
+ "k_proj",
26
+ "q_proj",
27
+ "up_proj",
28
+ "down_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87310ce0a05182d5ca69869b73e29ff1261b9697b88b5e162b6be98a629e886
3
+ size 80014016
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "codellama/CodeLlama-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "_load_in_4bit": true,
22
+ "_load_in_8bit": false,
23
+ "bnb_4bit_compute_dtype": "float32",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "fp4",
26
+ "bnb_4bit_use_double_quant": false,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_scaling": null,
37
+ "rope_theta": 1000000,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.40.0.dev0",
41
+ "use_cache": false,
42
+ "vocab_size": 32016
43
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.40.0.dev0"
7
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7451fe4c47051304a6f10dced459c514956ce6cd83cafe4c8d2b93ccae808d27
3
+ size 4968219133
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9c3a772bde1a57234fd76960661c7f5fa95b9d785a7cf318fcfcf04964eaca0
3
+ size 4977946827
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb68f78b3314e6483712a2ea1289d6d13b09310026d416c9687467b91d2cd6a8
3
+ size 3611152627
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,746 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13557047296
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.down_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.down_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.mlp.up_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.mlp.up_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.0.mlp.up_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.0.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.0.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.0.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.0.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.0.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.0.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.0.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.0.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.0.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.0.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.0.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.0.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.1.mlp.down_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.1.mlp.down_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.1.mlp.down_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.1.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.1.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.1.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.1.mlp.up_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.1.mlp.up_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.1.mlp.up_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.1.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.1.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.1.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.1.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.1.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.1.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.1.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.1.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.1.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.layers.1.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
52
+ "model.layers.1.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.layers.1.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
54
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
55
+ "model.layers.10.mlp.down_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
56
+ "model.layers.10.mlp.down_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
57
+ "model.layers.10.mlp.down_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
58
+ "model.layers.10.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.layers.10.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
60
+ "model.layers.10.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
61
+ "model.layers.10.mlp.up_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
62
+ "model.layers.10.mlp.up_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
63
+ "model.layers.10.mlp.up_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
64
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
65
+ "model.layers.10.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
66
+ "model.layers.10.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
67
+ "model.layers.10.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
68
+ "model.layers.10.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
69
+ "model.layers.10.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
70
+ "model.layers.10.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
71
+ "model.layers.10.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
72
+ "model.layers.10.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
73
+ "model.layers.10.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
74
+ "model.layers.10.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
75
+ "model.layers.10.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
76
+ "model.layers.10.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
77
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.11.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.11.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.11.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.11.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
82
+ "model.layers.11.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
83
+ "model.layers.11.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
84
+ "model.layers.11.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.11.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.11.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.11.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
89
+ "model.layers.11.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
90
+ "model.layers.11.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
91
+ "model.layers.11.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
92
+ "model.layers.11.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
93
+ "model.layers.11.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
94
+ "model.layers.11.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
95
+ "model.layers.11.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
96
+ "model.layers.11.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
97
+ "model.layers.11.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
98
+ "model.layers.11.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
99
+ "model.layers.11.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
100
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.12.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.12.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.12.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.12.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.12.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.12.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.12.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.12.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.12.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.12.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.12.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.12.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.12.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.12.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.12.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.12.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.12.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.12.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.12.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.12.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.12.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.13.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.13.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.13.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.13.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.13.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.13.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.13.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.13.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.13.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.13.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.13.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.13.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.13.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.13.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.13.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.13.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.13.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.13.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.13.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.13.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.13.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.14.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.14.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.14.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.14.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.14.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.14.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.14.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.14.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.14.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.14.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.14.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.14.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.14.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.14.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.14.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.14.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.14.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.14.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.14.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.14.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.14.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.15.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.15.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.15.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.15.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.15.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.15.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.15.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.15.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.15.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.15.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.15.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.15.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.15.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.15.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.15.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.15.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.15.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.15.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.15.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.15.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.15.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.16.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.16.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.16.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.16.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.16.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.16.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.16.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.16.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.16.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.16.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.16.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.16.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.16.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.16.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.16.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.16.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.16.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
211
+ "model.layers.16.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
212
+ "model.layers.16.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.layers.16.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
214
+ "model.layers.16.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
216
+ "model.layers.17.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
217
+ "model.layers.17.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
218
+ "model.layers.17.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
219
+ "model.layers.17.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
220
+ "model.layers.17.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
221
+ "model.layers.17.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
222
+ "model.layers.17.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
223
+ "model.layers.17.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
224
+ "model.layers.17.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
225
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
226
+ "model.layers.17.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
227
+ "model.layers.17.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.17.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
229
+ "model.layers.17.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.17.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.17.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.17.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.17.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
234
+ "model.layers.17.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
235
+ "model.layers.17.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
236
+ "model.layers.17.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
237
+ "model.layers.17.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
238
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
239
+ "model.layers.18.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
240
+ "model.layers.18.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
241
+ "model.layers.18.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
242
+ "model.layers.18.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
243
+ "model.layers.18.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
244
+ "model.layers.18.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
245
+ "model.layers.18.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
246
+ "model.layers.18.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
247
+ "model.layers.18.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
248
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
249
+ "model.layers.18.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
250
+ "model.layers.18.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
251
+ "model.layers.18.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
252
+ "model.layers.18.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
253
+ "model.layers.18.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
254
+ "model.layers.18.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
255
+ "model.layers.18.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
256
+ "model.layers.18.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
257
+ "model.layers.18.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
258
+ "model.layers.18.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
259
+ "model.layers.18.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
260
+ "model.layers.18.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
261
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
262
+ "model.layers.19.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
263
+ "model.layers.19.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
264
+ "model.layers.19.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
265
+ "model.layers.19.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
266
+ "model.layers.19.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
267
+ "model.layers.19.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
268
+ "model.layers.19.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
269
+ "model.layers.19.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
270
+ "model.layers.19.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
271
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
272
+ "model.layers.19.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
273
+ "model.layers.19.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
274
+ "model.layers.19.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
275
+ "model.layers.19.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
276
+ "model.layers.19.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
277
+ "model.layers.19.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
278
+ "model.layers.19.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
279
+ "model.layers.19.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
280
+ "model.layers.19.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
281
+ "model.layers.19.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
282
+ "model.layers.19.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
283
+ "model.layers.19.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
284
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
285
+ "model.layers.2.mlp.down_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
286
+ "model.layers.2.mlp.down_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
287
+ "model.layers.2.mlp.down_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
288
+ "model.layers.2.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
289
+ "model.layers.2.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
290
+ "model.layers.2.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
291
+ "model.layers.2.mlp.up_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
292
+ "model.layers.2.mlp.up_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
293
+ "model.layers.2.mlp.up_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
294
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
295
+ "model.layers.2.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
296
+ "model.layers.2.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
297
+ "model.layers.2.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
298
+ "model.layers.2.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
299
+ "model.layers.2.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
300
+ "model.layers.2.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
301
+ "model.layers.2.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
302
+ "model.layers.2.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
303
+ "model.layers.2.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
304
+ "model.layers.2.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
305
+ "model.layers.2.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
306
+ "model.layers.2.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
307
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
308
+ "model.layers.20.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
309
+ "model.layers.20.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
310
+ "model.layers.20.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
311
+ "model.layers.20.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
312
+ "model.layers.20.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
313
+ "model.layers.20.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
314
+ "model.layers.20.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
315
+ "model.layers.20.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
316
+ "model.layers.20.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
317
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
318
+ "model.layers.20.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
319
+ "model.layers.20.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
320
+ "model.layers.20.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
321
+ "model.layers.20.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
322
+ "model.layers.20.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
323
+ "model.layers.20.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
324
+ "model.layers.20.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
325
+ "model.layers.20.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
326
+ "model.layers.20.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
327
+ "model.layers.20.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
328
+ "model.layers.20.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
329
+ "model.layers.20.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
330
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
331
+ "model.layers.21.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
332
+ "model.layers.21.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
333
+ "model.layers.21.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
334
+ "model.layers.21.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
335
+ "model.layers.21.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
336
+ "model.layers.21.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
337
+ "model.layers.21.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
338
+ "model.layers.21.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
339
+ "model.layers.21.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
340
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
341
+ "model.layers.21.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
342
+ "model.layers.21.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
343
+ "model.layers.21.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
344
+ "model.layers.21.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
345
+ "model.layers.21.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
346
+ "model.layers.21.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
347
+ "model.layers.21.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
348
+ "model.layers.21.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
349
+ "model.layers.21.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
350
+ "model.layers.21.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
351
+ "model.layers.21.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
352
+ "model.layers.21.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
353
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
354
+ "model.layers.22.mlp.down_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
355
+ "model.layers.22.mlp.down_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
356
+ "model.layers.22.mlp.down_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
357
+ "model.layers.22.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
358
+ "model.layers.22.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
359
+ "model.layers.22.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
360
+ "model.layers.22.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
361
+ "model.layers.22.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
362
+ "model.layers.22.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
363
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
364
+ "model.layers.22.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
365
+ "model.layers.22.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
366
+ "model.layers.22.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
367
+ "model.layers.22.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
368
+ "model.layers.22.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
369
+ "model.layers.22.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
370
+ "model.layers.22.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
371
+ "model.layers.22.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
372
+ "model.layers.22.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
373
+ "model.layers.22.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
374
+ "model.layers.22.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
375
+ "model.layers.22.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
376
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
377
+ "model.layers.23.mlp.down_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
378
+ "model.layers.23.mlp.down_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
379
+ "model.layers.23.mlp.down_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
380
+ "model.layers.23.mlp.gate_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
381
+ "model.layers.23.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
382
+ "model.layers.23.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
383
+ "model.layers.23.mlp.up_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
384
+ "model.layers.23.mlp.up_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
385
+ "model.layers.23.mlp.up_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
386
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
387
+ "model.layers.23.self_attn.k_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
388
+ "model.layers.23.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
389
+ "model.layers.23.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
390
+ "model.layers.23.self_attn.o_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
391
+ "model.layers.23.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
392
+ "model.layers.23.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
393
+ "model.layers.23.self_attn.q_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
394
+ "model.layers.23.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
395
+ "model.layers.23.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
396
+ "model.layers.23.self_attn.v_proj.base_layer.weight": "pytorch_model-00002-of-00003.bin",
397
+ "model.layers.23.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
398
+ "model.layers.23.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
399
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
400
+ "model.layers.24.mlp.down_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
401
+ "model.layers.24.mlp.down_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
402
+ "model.layers.24.mlp.down_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
403
+ "model.layers.24.mlp.gate_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
404
+ "model.layers.24.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
405
+ "model.layers.24.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
406
+ "model.layers.24.mlp.up_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
407
+ "model.layers.24.mlp.up_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
408
+ "model.layers.24.mlp.up_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
409
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
410
+ "model.layers.24.self_attn.k_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
411
+ "model.layers.24.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
412
+ "model.layers.24.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
413
+ "model.layers.24.self_attn.o_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
414
+ "model.layers.24.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
415
+ "model.layers.24.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
416
+ "model.layers.24.self_attn.q_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
417
+ "model.layers.24.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
418
+ "model.layers.24.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
419
+ "model.layers.24.self_attn.v_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
420
+ "model.layers.24.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
421
+ "model.layers.24.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
422
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
423
+ "model.layers.25.mlp.down_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
424
+ "model.layers.25.mlp.down_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
425
+ "model.layers.25.mlp.down_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
426
+ "model.layers.25.mlp.gate_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
427
+ "model.layers.25.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
428
+ "model.layers.25.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
429
+ "model.layers.25.mlp.up_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
430
+ "model.layers.25.mlp.up_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
431
+ "model.layers.25.mlp.up_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
432
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
433
+ "model.layers.25.self_attn.k_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
434
+ "model.layers.25.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
435
+ "model.layers.25.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
436
+ "model.layers.25.self_attn.o_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
437
+ "model.layers.25.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
438
+ "model.layers.25.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
439
+ "model.layers.25.self_attn.q_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
440
+ "model.layers.25.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
441
+ "model.layers.25.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
442
+ "model.layers.25.self_attn.v_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
443
+ "model.layers.25.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
444
+ "model.layers.25.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
445
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
446
+ "model.layers.26.mlp.down_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
447
+ "model.layers.26.mlp.down_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
448
+ "model.layers.26.mlp.down_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
449
+ "model.layers.26.mlp.gate_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
450
+ "model.layers.26.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
451
+ "model.layers.26.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
452
+ "model.layers.26.mlp.up_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
453
+ "model.layers.26.mlp.up_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
454
+ "model.layers.26.mlp.up_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
455
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
456
+ "model.layers.26.self_attn.k_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
457
+ "model.layers.26.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
458
+ "model.layers.26.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
459
+ "model.layers.26.self_attn.o_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
460
+ "model.layers.26.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
461
+ "model.layers.26.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
462
+ "model.layers.26.self_attn.q_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
463
+ "model.layers.26.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
464
+ "model.layers.26.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
465
+ "model.layers.26.self_attn.v_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
466
+ "model.layers.26.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
467
+ "model.layers.26.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
468
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
469
+ "model.layers.27.mlp.down_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
470
+ "model.layers.27.mlp.down_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
471
+ "model.layers.27.mlp.down_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
472
+ "model.layers.27.mlp.gate_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
473
+ "model.layers.27.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
474
+ "model.layers.27.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
475
+ "model.layers.27.mlp.up_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
476
+ "model.layers.27.mlp.up_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
477
+ "model.layers.27.mlp.up_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
478
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
479
+ "model.layers.27.self_attn.k_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
480
+ "model.layers.27.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
481
+ "model.layers.27.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
482
+ "model.layers.27.self_attn.o_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
483
+ "model.layers.27.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
484
+ "model.layers.27.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
485
+ "model.layers.27.self_attn.q_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
486
+ "model.layers.27.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
487
+ "model.layers.27.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
488
+ "model.layers.27.self_attn.v_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
489
+ "model.layers.27.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
490
+ "model.layers.27.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
491
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
492
+ "model.layers.28.mlp.down_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
493
+ "model.layers.28.mlp.down_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
494
+ "model.layers.28.mlp.down_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
495
+ "model.layers.28.mlp.gate_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
496
+ "model.layers.28.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
497
+ "model.layers.28.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
498
+ "model.layers.28.mlp.up_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
499
+ "model.layers.28.mlp.up_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
500
+ "model.layers.28.mlp.up_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
501
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
502
+ "model.layers.28.self_attn.k_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
503
+ "model.layers.28.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
504
+ "model.layers.28.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
505
+ "model.layers.28.self_attn.o_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
506
+ "model.layers.28.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
507
+ "model.layers.28.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
508
+ "model.layers.28.self_attn.q_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
509
+ "model.layers.28.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
510
+ "model.layers.28.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
511
+ "model.layers.28.self_attn.v_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
512
+ "model.layers.28.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
513
+ "model.layers.28.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
514
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
515
+ "model.layers.29.mlp.down_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
516
+ "model.layers.29.mlp.down_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
517
+ "model.layers.29.mlp.down_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
518
+ "model.layers.29.mlp.gate_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
519
+ "model.layers.29.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
520
+ "model.layers.29.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
521
+ "model.layers.29.mlp.up_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
522
+ "model.layers.29.mlp.up_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
523
+ "model.layers.29.mlp.up_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
524
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
525
+ "model.layers.29.self_attn.k_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
526
+ "model.layers.29.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
527
+ "model.layers.29.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
528
+ "model.layers.29.self_attn.o_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
529
+ "model.layers.29.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
530
+ "model.layers.29.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
531
+ "model.layers.29.self_attn.q_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
532
+ "model.layers.29.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
533
+ "model.layers.29.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
534
+ "model.layers.29.self_attn.v_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
535
+ "model.layers.29.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
536
+ "model.layers.29.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
537
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
538
+ "model.layers.3.mlp.down_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
539
+ "model.layers.3.mlp.down_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
540
+ "model.layers.3.mlp.down_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
541
+ "model.layers.3.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
542
+ "model.layers.3.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
543
+ "model.layers.3.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
544
+ "model.layers.3.mlp.up_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
545
+ "model.layers.3.mlp.up_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
546
+ "model.layers.3.mlp.up_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
547
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
548
+ "model.layers.3.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
549
+ "model.layers.3.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
550
+ "model.layers.3.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
551
+ "model.layers.3.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
552
+ "model.layers.3.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
553
+ "model.layers.3.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
554
+ "model.layers.3.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
555
+ "model.layers.3.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
556
+ "model.layers.3.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
557
+ "model.layers.3.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
558
+ "model.layers.3.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
559
+ "model.layers.3.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
560
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
561
+ "model.layers.30.mlp.down_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
562
+ "model.layers.30.mlp.down_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
563
+ "model.layers.30.mlp.down_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
564
+ "model.layers.30.mlp.gate_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
565
+ "model.layers.30.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
566
+ "model.layers.30.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
567
+ "model.layers.30.mlp.up_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
568
+ "model.layers.30.mlp.up_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
569
+ "model.layers.30.mlp.up_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
570
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
571
+ "model.layers.30.self_attn.k_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
572
+ "model.layers.30.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
573
+ "model.layers.30.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
574
+ "model.layers.30.self_attn.o_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
575
+ "model.layers.30.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
576
+ "model.layers.30.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
577
+ "model.layers.30.self_attn.q_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
578
+ "model.layers.30.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
579
+ "model.layers.30.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
580
+ "model.layers.30.self_attn.v_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
581
+ "model.layers.30.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
582
+ "model.layers.30.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
583
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
584
+ "model.layers.31.mlp.down_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
585
+ "model.layers.31.mlp.down_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
586
+ "model.layers.31.mlp.down_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
587
+ "model.layers.31.mlp.gate_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
588
+ "model.layers.31.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
589
+ "model.layers.31.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
590
+ "model.layers.31.mlp.up_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
591
+ "model.layers.31.mlp.up_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
592
+ "model.layers.31.mlp.up_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
593
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
594
+ "model.layers.31.self_attn.k_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
595
+ "model.layers.31.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
596
+ "model.layers.31.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
597
+ "model.layers.31.self_attn.o_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
598
+ "model.layers.31.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
599
+ "model.layers.31.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
600
+ "model.layers.31.self_attn.q_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
601
+ "model.layers.31.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
602
+ "model.layers.31.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
603
+ "model.layers.31.self_attn.v_proj.base_layer.weight": "pytorch_model-00003-of-00003.bin",
604
+ "model.layers.31.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
605
+ "model.layers.31.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
606
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
607
+ "model.layers.4.mlp.down_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
608
+ "model.layers.4.mlp.down_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
609
+ "model.layers.4.mlp.down_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
610
+ "model.layers.4.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
611
+ "model.layers.4.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
612
+ "model.layers.4.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
613
+ "model.layers.4.mlp.up_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
614
+ "model.layers.4.mlp.up_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
615
+ "model.layers.4.mlp.up_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
616
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
617
+ "model.layers.4.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
618
+ "model.layers.4.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
619
+ "model.layers.4.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
620
+ "model.layers.4.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
621
+ "model.layers.4.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
622
+ "model.layers.4.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
623
+ "model.layers.4.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
624
+ "model.layers.4.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
625
+ "model.layers.4.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
626
+ "model.layers.4.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
627
+ "model.layers.4.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
628
+ "model.layers.4.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
629
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
630
+ "model.layers.5.mlp.down_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
631
+ "model.layers.5.mlp.down_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
632
+ "model.layers.5.mlp.down_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
633
+ "model.layers.5.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
634
+ "model.layers.5.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
635
+ "model.layers.5.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
636
+ "model.layers.5.mlp.up_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
637
+ "model.layers.5.mlp.up_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
638
+ "model.layers.5.mlp.up_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
639
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
640
+ "model.layers.5.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
641
+ "model.layers.5.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
642
+ "model.layers.5.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
643
+ "model.layers.5.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
644
+ "model.layers.5.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
645
+ "model.layers.5.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
646
+ "model.layers.5.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
647
+ "model.layers.5.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
648
+ "model.layers.5.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
649
+ "model.layers.5.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
650
+ "model.layers.5.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
651
+ "model.layers.5.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
652
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
653
+ "model.layers.6.mlp.down_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
654
+ "model.layers.6.mlp.down_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
655
+ "model.layers.6.mlp.down_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
656
+ "model.layers.6.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
657
+ "model.layers.6.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
658
+ "model.layers.6.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
659
+ "model.layers.6.mlp.up_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
660
+ "model.layers.6.mlp.up_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
661
+ "model.layers.6.mlp.up_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
662
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
663
+ "model.layers.6.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
664
+ "model.layers.6.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
665
+ "model.layers.6.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
666
+ "model.layers.6.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
667
+ "model.layers.6.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
668
+ "model.layers.6.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
669
+ "model.layers.6.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
670
+ "model.layers.6.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
671
+ "model.layers.6.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
672
+ "model.layers.6.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
673
+ "model.layers.6.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
674
+ "model.layers.6.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
675
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
676
+ "model.layers.7.mlp.down_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
677
+ "model.layers.7.mlp.down_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
678
+ "model.layers.7.mlp.down_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
679
+ "model.layers.7.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
680
+ "model.layers.7.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
681
+ "model.layers.7.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
682
+ "model.layers.7.mlp.up_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
683
+ "model.layers.7.mlp.up_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
684
+ "model.layers.7.mlp.up_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
685
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
686
+ "model.layers.7.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
687
+ "model.layers.7.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
688
+ "model.layers.7.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
689
+ "model.layers.7.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
690
+ "model.layers.7.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
691
+ "model.layers.7.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
692
+ "model.layers.7.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
693
+ "model.layers.7.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
694
+ "model.layers.7.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
695
+ "model.layers.7.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
696
+ "model.layers.7.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
697
+ "model.layers.7.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
698
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
699
+ "model.layers.8.mlp.down_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
700
+ "model.layers.8.mlp.down_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
701
+ "model.layers.8.mlp.down_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
702
+ "model.layers.8.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
703
+ "model.layers.8.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
704
+ "model.layers.8.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
705
+ "model.layers.8.mlp.up_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
706
+ "model.layers.8.mlp.up_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
707
+ "model.layers.8.mlp.up_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
708
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
709
+ "model.layers.8.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
710
+ "model.layers.8.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
711
+ "model.layers.8.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
712
+ "model.layers.8.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
713
+ "model.layers.8.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
714
+ "model.layers.8.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
715
+ "model.layers.8.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
716
+ "model.layers.8.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
717
+ "model.layers.8.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
718
+ "model.layers.8.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
719
+ "model.layers.8.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
720
+ "model.layers.8.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
721
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
722
+ "model.layers.9.mlp.down_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
723
+ "model.layers.9.mlp.down_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
724
+ "model.layers.9.mlp.down_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
725
+ "model.layers.9.mlp.gate_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
726
+ "model.layers.9.mlp.gate_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
727
+ "model.layers.9.mlp.gate_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
728
+ "model.layers.9.mlp.up_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
729
+ "model.layers.9.mlp.up_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
730
+ "model.layers.9.mlp.up_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
731
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
732
+ "model.layers.9.self_attn.k_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
733
+ "model.layers.9.self_attn.k_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
734
+ "model.layers.9.self_attn.k_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
735
+ "model.layers.9.self_attn.o_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
736
+ "model.layers.9.self_attn.o_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
737
+ "model.layers.9.self_attn.o_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
738
+ "model.layers.9.self_attn.q_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
739
+ "model.layers.9.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
740
+ "model.layers.9.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
741
+ "model.layers.9.self_attn.v_proj.base_layer.weight": "pytorch_model-00001-of-00003.bin",
742
+ "model.layers.9.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
743
+ "model.layers.9.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
744
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin"
745
+ }
746
+ }
runs/Apr29_13-09-35_4da20d8147fc/events.out.tfevents.1714396178.4da20d8147fc.11908.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063e0507cca1bc24ec2d7d8b6c277e5d41f454129c1615b4b083666d702d4fe0
3
+ size 40569
runs/Apr29_13-13-12_4da20d8147fc/events.out.tfevents.1714396394.4da20d8147fc.14040.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19d8189a8b260ba0ae9212664c88a2e3ec95a543196f87b6e7f25b2afc2b08bc
3
+ size 156788
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": "</s>",
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32007": {
30
+ "content": "▁<PRE>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32008": {
38
+ "content": "▁<SUF>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32009": {
46
+ "content": "▁<MID>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32010": {
54
+ "content": "▁<EOT>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "▁<PRE>",
64
+ "▁<MID>",
65
+ "▁<SUF>",
66
+ "▁<EOT>"
67
+ ],
68
+ "bos_token": "<s>",
69
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
70
+ "clean_up_tokenization_spaces": false,
71
+ "eos_token": "</s>",
72
+ "eot_token": "▁<EOT>",
73
+ "fill_token": "<FILL_ME>",
74
+ "legacy": null,
75
+ "middle_token": "▁<MID>",
76
+ "model_max_length": 1000000000000000019884624838656,
77
+ "pad_token": "</s>",
78
+ "prefix_token": "▁<PRE>",
79
+ "sp_model_kwargs": {},
80
+ "suffix_first": false,
81
+ "suffix_token": "▁<SUF>",
82
+ "tokenizer_class": "CodeLlamaTokenizer",
83
+ "unk_token": "<unk>",
84
+ "use_default_system_prompt": false,
85
+ "use_fast": true
86
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b563bc7bd640dd61652594f80367049033a373c338757b35d6dfc22aa5374687
3
+ size 5048