qnguyen3 commited on
Commit
218a615
1 Parent(s): 243efab

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-3B
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: outputs/gelato-3b
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.1`
19
+ ```yaml
20
+ base_model: Qwen/Qwen2.5-3B
21
+ load_in_8bit: false
22
+ load_in_4bit: false
23
+ strict: false
24
+
25
+ datasets:
26
+ - path: arcee-ai/eval_tome
27
+ type: sharegpt
28
+ conversation: chatml
29
+ - path: arcee-ai/math_code_5k_claude
30
+ type: sharegpt
31
+ conversation: chatml
32
+ split: validation
33
+ - path: Undi95/Capybara-ShareGPT
34
+ type: sharegpt
35
+ conversation: chatml
36
+ dataset_prepared_path:
37
+ val_set_size: 0.0
38
+
39
+ sequence_len: 8192
40
+ sample_packing: true
41
+
42
+ lora_fan_in_fan_out:
43
+ wandb_project: qwen2.5-3b-gelato
44
+ wandb_entity:
45
+ wandb_watch:
46
+ wandb_name:
47
+ wandb_log_model:
48
+ output_dir: ./outputs/gelato-3b
49
+ gradient_accumulation_steps: 8
50
+ micro_batch_size: 2
51
+ num_epochs: 4
52
+ optimizer: adamw_bnb_8bit
53
+ torchdistx_path:
54
+ lr_scheduler: cosine
55
+ learning_rate: 0.0002
56
+ train_on_inputs: false
57
+ group_by_length: false
58
+ bf16: auto
59
+ fp16:
60
+ tf32: true
61
+ gradient_checkpointing: true
62
+ early_stopping_patience:
63
+ resume_from_checkpoint:
64
+ local_rank:
65
+ logging_steps: 1
66
+ xformers_attention:
67
+ flash_attention: true
68
+ gptq_groupsize:
69
+ s2_attention:
70
+ gptq_model_v1:
71
+ warmup_steps: 50
72
+ evals_per_epoch:
73
+ saves_per_epoch: 1
74
+ debug:
75
+ deepspeed: deepspeed_configs/zero3_bf16_cpuoffload_params.json
76
+ weight_decay: 0.1
77
+ fsdp:
78
+ fsdp_config:
79
+ special_tokens:
80
+ eos_token: "<|im_end|>"
81
+ bos_token: "<|im_start|>"
82
+
83
+ ```
84
+
85
+ </details><br>
86
+
87
+ # outputs/gelato-3b
88
+
89
+ This model is a fine-tuned version of [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B) on the None dataset.
90
+
91
+ ## Model description
92
+
93
+ More information needed
94
+
95
+ ## Intended uses & limitations
96
+
97
+ More information needed
98
+
99
+ ## Training and evaluation data
100
+
101
+ More information needed
102
+
103
+ ## Training procedure
104
+
105
+ ### Training hyperparameters
106
+
107
+ The following hyperparameters were used during training:
108
+ - learning_rate: 0.0002
109
+ - train_batch_size: 2
110
+ - eval_batch_size: 2
111
+ - seed: 42
112
+ - distributed_type: multi-GPU
113
+ - num_devices: 4
114
+ - gradient_accumulation_steps: 8
115
+ - total_train_batch_size: 64
116
+ - total_eval_batch_size: 8
117
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
118
+ - lr_scheduler_type: cosine
119
+ - lr_scheduler_warmup_steps: 50
120
+ - num_epochs: 4
121
+
122
+ ### Training results
123
+
124
+
125
+
126
+ ### Framework versions
127
+
128
+ - Transformers 4.45.1
129
+ - Pytorch 2.3.1+cu121
130
+ - Datasets 2.21.0
131
+ - Tokenizers 0.20.0
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-3B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151644,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 36,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 36,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.45.1",
26
+ "use_cache": false,
27
+ "use_mrope": false,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "max_new_tokens": 2048,
6
+ "transformers_version": "4.45.1"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d38d9a351e5c98ab53d26184f5df2a2d6ee0520788b3a3edf3d49696224301
3
+ size 4957560304
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac538082dc8a7a28a2170ab6a45a48d7ffde50faf2e1a20ded87ee25f99b567
3
+ size 1214366696
model.safetensors.index.json ADDED
@@ -0,0 +1,441 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6171877376
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
169
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
172
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
181
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
184
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
193
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
196
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
198
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
205
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
208
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
210
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
217
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
220
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
222
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
229
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
232
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
234
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
241
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
244
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
246
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
253
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
256
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
258
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
265
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
268
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
270
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
277
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
280
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
282
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
301
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
304
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
306
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
313
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
316
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
318
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
325
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
328
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
330
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
337
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
340
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
341
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
342
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
343
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
349
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
350
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
352
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
354
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
361
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
362
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
364
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
366
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
368
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
373
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
385
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
388
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
397
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
402
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
409
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
412
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
421
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
422
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
424
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
433
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
434
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
436
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
439
+ "model.norm.weight": "model-00002-of-00002.safetensors"
440
+ }
441
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "bos_token": {
18
+ "content": "<|im_start|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "eos_token": {
25
+ "content": "<|im_end|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "pad_token": {
32
+ "content": "<|endoftext|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": "<|im_start|>",
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef649763bba88ab077d8402ae72583caf8897a5dc6b16e92148931cc78af2ae
3
+ size 8248
vocab.json ADDED
The diff for this file is too large to render. See raw diff