Hugging Face's logo

pandalin98
/
ITFormer-3B

Safetensors
vlm_model
Model card Files
xet
 Community
pandalin98 commited on
Commit
a5daa86
·
verified ·
1 Parent(s): ab1c2f9

Upload ITFormer 3B model

Browse files
Files changed (23) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. chat_template.jinja +54 -0
  4. config.json +11 -0
  5. generation_config.json +4 -0
  6. merges.txt +0 -0
  7. model-00001-of-00003.safetensors +3 -0
  8. model-00002-of-00003.safetensors +3 -0
  9. model-00003-of-00003.safetensors +3 -0
  10. model.safetensors.index.json +592 -0
  11. optimizer.pt +3 -0
  12. rng_state_0.pth +3 -0
  13. rng_state_1.pth +3 -0
  14. rng_state_2.pth +3 -0
  15. rng_state_3.pth +3 -0
  16. scaler.pt +3 -0
  17. scheduler.pt +3 -0
  18. special_tokens_map.json +31 -0
  19. tokenizer.json +3 -0
  20. tokenizer_config.json +207 -0
  21. trainer_state.json +622 -0
  22. training_args.bin +3 -0
  23. vocab.json +0 -0
.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
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
+ }
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "TLM"
4
+ ],
5
+ "freeze_ts_model": true,
6
+ "llm_model_path": "LLM/Qwen2.5-3B-Instruct",
7
+ "model_type": "vlm_model",
8
+ "torch_dtype": "float32",
9
+ "transformers_version": "4.54.1",
10
+ "ts_pad_num": 25
11
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.54.1"
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0fd80a85b23a0499fd26a3330d43b61cbafee69f43490dc7a53cd16335bb97
3
+ size 4982133056
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ef716a46d99332f34de4bcfc0333c8b72e50a85d92d22f45d9f37ca8c601fb
3
+ size 4932951256
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7d3b57c658a0724d431f08cb306d0b9a24b6f01d659c890a67a1835212e492
3
+ size 2758163240
model.safetensors.index.json ADDED
@@ -0,0 +1,592 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 3154854076,
4
+ "total_size": 12673176304
5
+ },
6
+ "weight_map": {
7
+ "fusion_project.bias": "model-00003-of-00003.safetensors",
8
+ "fusion_project.weight": "model-00003-of-00003.safetensors",
9
+ "itformer.cycle_pos.pe": "model-00003-of-00003.safetensors",
10
+ "itformer.instruc_pos.pe": "model-00003-of-00003.safetensors",
11
+ "itformer.layers.0.feed_forward_instruct.0.bias": "model-00003-of-00003.safetensors",
12
+ "itformer.layers.0.feed_forward_instruct.0.weight": "model-00003-of-00003.safetensors",
13
+ "itformer.layers.0.feed_forward_instruct.1.bias": "model-00003-of-00003.safetensors",
14
+ "itformer.layers.0.feed_forward_instruct.1.weight": "model-00003-of-00003.safetensors",
15
+ "itformer.layers.0.feed_forward_instruct.4.bias": "model-00003-of-00003.safetensors",
16
+ "itformer.layers.0.feed_forward_instruct.4.weight": "model-00003-of-00003.safetensors",
17
+ "itformer.layers.0.feed_forward_prefix.0.bias": "model-00003-of-00003.safetensors",
18
+ "itformer.layers.0.feed_forward_prefix.0.weight": "model-00003-of-00003.safetensors",
19
+ "itformer.layers.0.feed_forward_prefix.1.bias": "model-00003-of-00003.safetensors",
20
+ "itformer.layers.0.feed_forward_prefix.1.weight": "model-00003-of-00003.safetensors",
21
+ "itformer.layers.0.feed_forward_prefix.4.bias": "model-00003-of-00003.safetensors",
22
+ "itformer.layers.0.feed_forward_prefix.4.weight": "model-00003-of-00003.safetensors",
23
+ "itformer.layers.0.it_attn.attn_it.channel_key_proj.bias": "model-00003-of-00003.safetensors",
24
+ "itformer.layers.0.it_attn.attn_it.channel_key_proj.weight": "model-00003-of-00003.safetensors",
25
+ "itformer.layers.0.it_attn.attn_it.channel_query_proj.bias": "model-00003-of-00003.safetensors",
26
+ "itformer.layers.0.it_attn.attn_it.channel_query_proj.weight": "model-00003-of-00003.safetensors",
27
+ "itformer.layers.0.it_attn.attn_it.channel_value_proj.bias": "model-00003-of-00003.safetensors",
28
+ "itformer.layers.0.it_attn.attn_it.channel_value_proj.weight": "model-00003-of-00003.safetensors",
29
+ "itformer.layers.0.it_attn.attn_it.key_proj.bias": "model-00003-of-00003.safetensors",
30
+ "itformer.layers.0.it_attn.attn_it.key_proj.weight": "model-00003-of-00003.safetensors",
31
+ "itformer.layers.0.it_attn.attn_it.proj.bias": "model-00003-of-00003.safetensors",
32
+ "itformer.layers.0.it_attn.attn_it.proj.weight": "model-00003-of-00003.safetensors",
33
+ "itformer.layers.0.it_attn.attn_it.query_proj.bias": "model-00003-of-00003.safetensors",
34
+ "itformer.layers.0.it_attn.attn_it.query_proj.weight": "model-00003-of-00003.safetensors",
35
+ "itformer.layers.0.it_attn.attn_it.value_proj.bias": "model-00003-of-00003.safetensors",
36
+ "itformer.layers.0.it_attn.attn_it.value_proj.weight": "model-00003-of-00003.safetensors",
37
+ "itformer.layers.0.it_attn.norm1.bias": "model-00003-of-00003.safetensors",
38
+ "itformer.layers.0.it_attn.norm1.weight": "model-00003-of-00003.safetensors",
39
+ "itformer.layers.0.self_attn.attn_seq.proj.bias": "model-00003-of-00003.safetensors",
40
+ "itformer.layers.0.self_attn.attn_seq.proj.weight": "model-00003-of-00003.safetensors",
41
+ "itformer.layers.0.self_attn.attn_seq.qkv.bias": "model-00003-of-00003.safetensors",
42
+ "itformer.layers.0.self_attn.attn_seq.qkv.weight": "model-00003-of-00003.safetensors",
43
+ "itformer.layers.0.self_attn.norm1.bias": "model-00003-of-00003.safetensors",
44
+ "itformer.layers.0.self_attn.norm1.weight": "model-00003-of-00003.safetensors",
45
+ "itformer.layers.1.feed_forward_instruct.0.bias": "model-00003-of-00003.safetensors",
46
+ "itformer.layers.1.feed_forward_instruct.0.weight": "model-00003-of-00003.safetensors",
47
+ "itformer.layers.1.feed_forward_instruct.1.bias": "model-00003-of-00003.safetensors",
48
+ "itformer.layers.1.feed_forward_instruct.1.weight": "model-00003-of-00003.safetensors",
49
+ "itformer.layers.1.feed_forward_instruct.4.bias": "model-00003-of-00003.safetensors",
50
+ "itformer.layers.1.feed_forward_instruct.4.weight": "model-00003-of-00003.safetensors",
51
+ "itformer.layers.1.feed_forward_prefix.0.bias": "model-00003-of-00003.safetensors",
52
+ "itformer.layers.1.feed_forward_prefix.0.weight": "model-00003-of-00003.safetensors",
53
+ "itformer.layers.1.feed_forward_prefix.1.bias": "model-00003-of-00003.safetensors",
54
+ "itformer.layers.1.feed_forward_prefix.1.weight": "model-00003-of-00003.safetensors",
55
+ "itformer.layers.1.feed_forward_prefix.4.bias": "model-00003-of-00003.safetensors",
56
+ "itformer.layers.1.feed_forward_prefix.4.weight": "model-00003-of-00003.safetensors",
57
+ "itformer.layers.1.it_attn.attn_it.channel_key_proj.bias": "model-00003-of-00003.safetensors",
58
+ "itformer.layers.1.it_attn.attn_it.channel_key_proj.weight": "model-00003-of-00003.safetensors",
59
+ "itformer.layers.1.it_attn.attn_it.channel_query_proj.bias": "model-00003-of-00003.safetensors",
60
+ "itformer.layers.1.it_attn.attn_it.channel_query_proj.weight": "model-00003-of-00003.safetensors",
61
+ "itformer.layers.1.it_attn.attn_it.channel_value_proj.bias": "model-00003-of-00003.safetensors",
62
+ "itformer.layers.1.it_attn.attn_it.channel_value_proj.weight": "model-00003-of-00003.safetensors",
63
+ "itformer.layers.1.it_attn.attn_it.key_proj.bias": "model-00003-of-00003.safetensors",
64
+ "itformer.layers.1.it_attn.attn_it.key_proj.weight": "model-00003-of-00003.safetensors",
65
+ "itformer.layers.1.it_attn.attn_it.proj.bias": "model-00003-of-00003.safetensors",
66
+ "itformer.layers.1.it_attn.attn_it.proj.weight": "model-00003-of-00003.safetensors",
67
+ "itformer.layers.1.it_attn.attn_it.query_proj.bias": "model-00003-of-00003.safetensors",
68
+ "itformer.layers.1.it_attn.attn_it.query_proj.weight": "model-00003-of-00003.safetensors",
69
+ "itformer.layers.1.it_attn.attn_it.value_proj.bias": "model-00003-of-00003.safetensors",
70
+ "itformer.layers.1.it_attn.attn_it.value_proj.weight": "model-00003-of-00003.safetensors",
71
+ "itformer.layers.1.it_attn.norm1.bias": "model-00003-of-00003.safetensors",
72
+ "itformer.layers.1.it_attn.norm1.weight": "model-00003-of-00003.safetensors",
73
+ "itformer.layers.1.self_attn.attn_seq.proj.bias": "model-00003-of-00003.safetensors",
74
+ "itformer.layers.1.self_attn.attn_seq.proj.weight": "model-00003-of-00003.safetensors",
75
+ "itformer.layers.1.self_attn.attn_seq.qkv.bias": "model-00003-of-00003.safetensors",
76
+ "itformer.layers.1.self_attn.attn_seq.qkv.weight": "model-00003-of-00003.safetensors",
77
+ "itformer.layers.1.self_attn.norm1.bias": "model-00003-of-00003.safetensors",
78
+ "itformer.layers.1.self_attn.norm1.weight": "model-00003-of-00003.safetensors",
79
+ "itformer.norm.bias": "model-00003-of-00003.safetensors",
80
+ "itformer.norm.weight": "model-00003-of-00003.safetensors",
81
+ "itformer.prefix_token": "model-00003-of-00003.safetensors",
82
+ "itformer.time_pos.pe": "model-00003-of-00003.safetensors",
83
+ "itformer.var_pos.pe": "model-00003-of-00003.safetensors",
84
+ "llm_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
85
+ "llm_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
86
+ "llm_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
87
+ "llm_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
88
+ "llm_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
89
+ "llm_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
90
+ "llm_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
91
+ "llm_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
92
+ "llm_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
93
+ "llm_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
94
+ "llm_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
95
+ "llm_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
96
+ "llm_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
97
+ "llm_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
98
+ "llm_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
99
+ "llm_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
100
+ "llm_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
101
+ "llm_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
102
+ "llm_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
103
+ "llm_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
104
+ "llm_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
105
+ "llm_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
106
+ "llm_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
107
+ "llm_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
108
+ "llm_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
109
+ "llm_model.model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
110
+ "llm_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
111
+ "llm_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
112
+ "llm_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
113
+ "llm_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
114
+ "llm_model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
115
+ "llm_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
116
+ "llm_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
117
+ "llm_model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
118
+ "llm_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
119
+ "llm_model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
120
+ "llm_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
121
+ "llm_model.model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
122
+ "llm_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
123
+ "llm_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
124
+ "llm_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
125
+ "llm_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
126
+ "llm_model.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
127
+ "llm_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
128
+ "llm_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
129
+ "llm_model.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
130
+ "llm_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
131
+ "llm_model.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
132
+ "llm_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
133
+ "llm_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
134
+ "llm_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
135
+ "llm_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
136
+ "llm_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
137
+ "llm_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
138
+ "llm_model.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
139
+ "llm_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
140
+ "llm_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
141
+ "llm_model.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
142
+ "llm_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
143
+ "llm_model.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
144
+ "llm_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
145
+ "llm_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
146
+ "llm_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
147
+ "llm_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
148
+ "llm_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
149
+ "llm_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
150
+ "llm_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
151
+ "llm_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
152
+ "llm_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
153
+ "llm_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
154
+ "llm_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
155
+ "llm_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
156
+ "llm_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
157
+ "llm_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
158
+ "llm_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
159
+ "llm_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
160
+ "llm_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
161
+ "llm_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
162
+ "llm_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
163
+ "llm_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
164
+ "llm_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
165
+ "llm_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
166
+ "llm_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
167
+ "llm_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
168
+ "llm_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
169
+ "llm_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
170
+ "llm_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
171
+ "llm_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
172
+ "llm_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
173
+ "llm_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
174
+ "llm_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
175
+ "llm_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
176
+ "llm_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
177
+ "llm_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
178
+ "llm_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
179
+ "llm_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
180
+ "llm_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
181
+ "llm_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
182
+ "llm_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
183
+ "llm_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
184
+ "llm_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
185
+ "llm_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
186
+ "llm_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
187
+ "llm_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
188
+ "llm_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
189
+ "llm_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
190
+ "llm_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
191
+ "llm_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
192
+ "llm_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
193
+ "llm_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
194
+ "llm_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
195
+ "llm_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
196
+ "llm_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
197
+ "llm_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
198
+ "llm_model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
199
+ "llm_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
200
+ "llm_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
201
+ "llm_model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
202
+ "llm_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
203
+ "llm_model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
204
+ "llm_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
205
+ "llm_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
206
+ "llm_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
207
+ "llm_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
208
+ "llm_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
209
+ "llm_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
210
+ "llm_model.model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
211
+ "llm_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
212
+ "llm_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
213
+ "llm_model.model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
214
+ "llm_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
215
+ "llm_model.model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
216
+ "llm_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
217
+ "llm_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
218
+ "llm_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
219
+ "llm_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
220
+ "llm_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
221
+ "llm_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
222
+ "llm_model.model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
223
+ "llm_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
224
+ "llm_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
225
+ "llm_model.model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
226
+ "llm_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
227
+ "llm_model.model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
228
+ "llm_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
229
+ "llm_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
230
+ "llm_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
231
+ "llm_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
232
+ "llm_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
233
+ "llm_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
234
+ "llm_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
235
+ "llm_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
236
+ "llm_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
237
+ "llm_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
238
+ "llm_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
239
+ "llm_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
240
+ "llm_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
241
+ "llm_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
242
+ "llm_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
243
+ "llm_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
244
+ "llm_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
245
+ "llm_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
246
+ "llm_model.model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
247
+ "llm_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
248
+ "llm_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
249
+ "llm_model.model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
250
+ "llm_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
251
+ "llm_model.model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
252
+ "llm_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
253
+ "llm_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
254
+ "llm_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
255
+ "llm_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
256
+ "llm_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
257
+ "llm_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
258
+ "llm_model.model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
259
+ "llm_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
260
+ "llm_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
261
+ "llm_model.model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
262
+ "llm_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
263
+ "llm_model.model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
264
+ "llm_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
265
+ "llm_model.model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
266
+ "llm_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
267
+ "llm_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
268
+ "llm_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
269
+ "llm_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
270
+ "llm_model.model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
271
+ "llm_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
272
+ "llm_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
273
+ "llm_model.model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
274
+ "llm_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
275
+ "llm_model.model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
276
+ "llm_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
277
+ "llm_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
278
+ "llm_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
279
+ "llm_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
280
+ "llm_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
281
+ "llm_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
282
+ "llm_model.model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
283
+ "llm_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
284
+ "llm_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
285
+ "llm_model.model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
286
+ "llm_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
287
+ "llm_model.model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
288
+ "llm_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
289
+ "llm_model.model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
290
+ "llm_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
291
+ "llm_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
292
+ "llm_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
293
+ "llm_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
294
+ "llm_model.model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
295
+ "llm_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
296
+ "llm_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
297
+ "llm_model.model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
298
+ "llm_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
299
+ "llm_model.model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
300
+ "llm_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
301
+ "llm_model.model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
302
+ "llm_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
303
+ "llm_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
304
+ "llm_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
305
+ "llm_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
306
+ "llm_model.model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
307
+ "llm_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
308
+ "llm_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
309
+ "llm_model.model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
310
+ "llm_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
311
+ "llm_model.model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
312
+ "llm_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
313
+ "llm_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
314
+ "llm_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
315
+ "llm_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
316
+ "llm_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
317
+ "llm_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
318
+ "llm_model.model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
319
+ "llm_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
320
+ "llm_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
321
+ "llm_model.model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
322
+ "llm_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
323
+ "llm_model.model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
324
+ "llm_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
325
+ "llm_model.model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
326
+ "llm_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
327
+ "llm_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
328
+ "llm_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
329
+ "llm_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
330
+ "llm_model.model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
331
+ "llm_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
332
+ "llm_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
333
+ "llm_model.model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
334
+ "llm_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
335
+ "llm_model.model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
336
+ "llm_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
337
+ "llm_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
338
+ "llm_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
339
+ "llm_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
340
+ "llm_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
341
+ "llm_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
342
+ "llm_model.model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
343
+ "llm_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
344
+ "llm_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
345
+ "llm_model.model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
346
+ "llm_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
347
+ "llm_model.model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
348
+ "llm_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
349
+ "llm_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
350
+ "llm_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
351
+ "llm_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
352
+ "llm_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
353
+ "llm_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
354
+ "llm_model.model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
355
+ "llm_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
356
+ "llm_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
357
+ "llm_model.model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
358
+ "llm_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
359
+ "llm_model.model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
360
+ "llm_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
361
+ "llm_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
362
+ "llm_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
363
+ "llm_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
364
+ "llm_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
365
+ "llm_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
366
+ "llm_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
367
+ "llm_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
368
+ "llm_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
369
+ "llm_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
370
+ "llm_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
371
+ "llm_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
372
+ "llm_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
373
+ "llm_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
374
+ "llm_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
375
+ "llm_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
376
+ "llm_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
377
+ "llm_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
378
+ "llm_model.model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
379
+ "llm_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
380
+ "llm_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
381
+ "llm_model.model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
382
+ "llm_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
383
+ "llm_model.model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
384
+ "llm_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
385
+ "llm_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
386
+ "llm_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
387
+ "llm_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
388
+ "llm_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
389
+ "llm_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
390
+ "llm_model.model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
391
+ "llm_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
392
+ "llm_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
393
+ "llm_model.model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
394
+ "llm_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
395
+ "llm_model.model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
396
+ "llm_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
397
+ "llm_model.model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
398
+ "llm_model.model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
399
+ "llm_model.model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
400
+ "llm_model.model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
401
+ "llm_model.model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
402
+ "llm_model.model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
403
+ "llm_model.model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
404
+ "llm_model.model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
405
+ "llm_model.model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
406
+ "llm_model.model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
407
+ "llm_model.model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
408
+ "llm_model.model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
409
+ "llm_model.model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
410
+ "llm_model.model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
411
+ "llm_model.model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
412
+ "llm_model.model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
413
+ "llm_model.model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
414
+ "llm_model.model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
415
+ "llm_model.model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
416
+ "llm_model.model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
417
+ "llm_model.model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
418
+ "llm_model.model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
419
+ "llm_model.model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
420
+ "llm_model.model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
421
+ "llm_model.model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
422
+ "llm_model.model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
423
+ "llm_model.model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
424
+ "llm_model.model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
425
+ "llm_model.model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
426
+ "llm_model.model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
427
+ "llm_model.model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
428
+ "llm_model.model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
429
+ "llm_model.model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
430
+ "llm_model.model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
431
+ "llm_model.model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
432
+ "llm_model.model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
433
+ "llm_model.model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
434
+ "llm_model.model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
435
+ "llm_model.model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
436
+ "llm_model.model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
437
+ "llm_model.model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
438
+ "llm_model.model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
439
+ "llm_model.model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
440
+ "llm_model.model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
441
+ "llm_model.model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
442
+ "llm_model.model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
443
+ "llm_model.model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
444
+ "llm_model.model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
445
+ "llm_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
446
+ "llm_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
447
+ "llm_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
448
+ "llm_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
449
+ "llm_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
450
+ "llm_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
451
+ "llm_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
452
+ "llm_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
453
+ "llm_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
454
+ "llm_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
455
+ "llm_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
456
+ "llm_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
457
+ "llm_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
458
+ "llm_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
459
+ "llm_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
460
+ "llm_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
461
+ "llm_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
462
+ "llm_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
463
+ "llm_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
464
+ "llm_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
465
+ "llm_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
466
+ "llm_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
467
+ "llm_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
468
+ "llm_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
469
+ "llm_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
470
+ "llm_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
471
+ "llm_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
472
+ "llm_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
473
+ "llm_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
474
+ "llm_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
475
+ "llm_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
476
+ "llm_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
477
+ "llm_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
478
+ "llm_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
479
+ "llm_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
480
+ "llm_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
481
+ "llm_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
482
+ "llm_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
483
+ "llm_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
484
+ "llm_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
485
+ "llm_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
486
+ "llm_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
487
+ "llm_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
488
+ "llm_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
489
+ "llm_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
490
+ "llm_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
491
+ "llm_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
492
+ "llm_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
493
+ "llm_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
494
+ "llm_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
495
+ "llm_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
496
+ "llm_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
497
+ "llm_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
498
+ "llm_model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
499
+ "llm_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
500
+ "llm_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
501
+ "llm_model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
502
+ "llm_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
503
+ "llm_model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
504
+ "llm_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
505
+ "llm_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
506
+ "llm_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
507
+ "llm_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
508
+ "llm_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
509
+ "llm_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
510
+ "llm_model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
511
+ "llm_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
512
+ "llm_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
513
+ "llm_model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
514
+ "llm_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
515
+ "llm_model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
516
+ "llm_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
517
+ "llm_model.model.norm.weight": "model-00003-of-00003.safetensors",
518
+ "query_project.bias": "model-00003-of-00003.safetensors",
519
+ "query_project.weight": "model-00003-of-00003.safetensors",
520
+ "ts_encoder.layers.0.feed_forward.fc1.bias": "model-00003-of-00003.safetensors",
521
+ "ts_encoder.layers.0.feed_forward.fc1.weight": "model-00003-of-00003.safetensors",
522
+ "ts_encoder.layers.0.feed_forward.fc2.bias": "model-00003-of-00003.safetensors",
523
+ "ts_encoder.layers.0.feed_forward.fc2.weight": "model-00003-of-00003.safetensors",
524
+ "ts_encoder.layers.0.seq_att_block.attn_seq.proj.bias": "model-00003-of-00003.safetensors",
525
+ "ts_encoder.layers.0.seq_att_block.attn_seq.proj.weight": "model-00003-of-00003.safetensors",
526
+ "ts_encoder.layers.0.seq_att_block.attn_seq.qkv.bias": "model-00003-of-00003.safetensors",
527
+ "ts_encoder.layers.0.seq_att_block.attn_seq.qkv.weight": "model-00003-of-00003.safetensors",
528
+ "ts_encoder.layers.0.seq_att_block.norm1.bias": "model-00003-of-00003.safetensors",
529
+ "ts_encoder.layers.0.seq_att_block.norm1.weight": "model-00003-of-00003.safetensors",
530
+ "ts_encoder.layers.0.var_att_block.attn_var.proj.bias": "model-00003-of-00003.safetensors",
531
+ "ts_encoder.layers.0.var_att_block.attn_var.proj.weight": "model-00003-of-00003.safetensors",
532
+ "ts_encoder.layers.0.var_att_block.attn_var.qkv.bias": "model-00003-of-00003.safetensors",
533
+ "ts_encoder.layers.0.var_att_block.attn_var.qkv.weight": "model-00003-of-00003.safetensors",
534
+ "ts_encoder.layers.0.var_att_block.norm1.bias": "model-00003-of-00003.safetensors",
535
+ "ts_encoder.layers.0.var_att_block.norm1.weight": "model-00003-of-00003.safetensors",
536
+ "ts_encoder.layers.1.feed_forward.fc1.bias": "model-00003-of-00003.safetensors",
537
+ "ts_encoder.layers.1.feed_forward.fc1.weight": "model-00003-of-00003.safetensors",
538
+ "ts_encoder.layers.1.feed_forward.fc2.bias": "model-00003-of-00003.safetensors",
539
+ "ts_encoder.layers.1.feed_forward.fc2.weight": "model-00003-of-00003.safetensors",
540
+ "ts_encoder.layers.1.seq_att_block.attn_seq.proj.bias": "model-00003-of-00003.safetensors",
541
+ "ts_encoder.layers.1.seq_att_block.attn_seq.proj.weight": "model-00003-of-00003.safetensors",
542
+ "ts_encoder.layers.1.seq_att_block.attn_seq.qkv.bias": "model-00003-of-00003.safetensors",
543
+ "ts_encoder.layers.1.seq_att_block.attn_seq.qkv.weight": "model-00003-of-00003.safetensors",
544
+ "ts_encoder.layers.1.seq_att_block.norm1.bias": "model-00003-of-00003.safetensors",
545
+ "ts_encoder.layers.1.seq_att_block.norm1.weight": "model-00003-of-00003.safetensors",
546
+ "ts_encoder.layers.1.var_att_block.attn_var.proj.bias": "model-00003-of-00003.safetensors",
547
+ "ts_encoder.layers.1.var_att_block.attn_var.proj.weight": "model-00003-of-00003.safetensors",
548
+ "ts_encoder.layers.1.var_att_block.attn_var.qkv.bias": "model-00003-of-00003.safetensors",
549
+ "ts_encoder.layers.1.var_att_block.attn_var.qkv.weight": "model-00003-of-00003.safetensors",
550
+ "ts_encoder.layers.1.var_att_block.norm1.bias": "model-00003-of-00003.safetensors",
551
+ "ts_encoder.layers.1.var_att_block.norm1.weight": "model-00003-of-00003.safetensors",
552
+ "ts_encoder.layers.2.feed_forward.fc1.bias": "model-00003-of-00003.safetensors",
553
+ "ts_encoder.layers.2.feed_forward.fc1.weight": "model-00003-of-00003.safetensors",
554
+ "ts_encoder.layers.2.feed_forward.fc2.bias": "model-00003-of-00003.safetensors",
555
+ "ts_encoder.layers.2.feed_forward.fc2.weight": "model-00003-of-00003.safetensors",
556
+ "ts_encoder.layers.2.seq_att_block.attn_seq.proj.bias": "model-00003-of-00003.safetensors",
557
+ "ts_encoder.layers.2.seq_att_block.attn_seq.proj.weight": "model-00003-of-00003.safetensors",
558
+ "ts_encoder.layers.2.seq_att_block.attn_seq.qkv.bias": "model-00003-of-00003.safetensors",
559
+ "ts_encoder.layers.2.seq_att_block.attn_seq.qkv.weight": "model-00003-of-00003.safetensors",
560
+ "ts_encoder.layers.2.seq_att_block.norm1.bias": "model-00003-of-00003.safetensors",
561
+ "ts_encoder.layers.2.seq_att_block.norm1.weight": "model-00003-of-00003.safetensors",
562
+ "ts_encoder.layers.2.var_att_block.attn_var.proj.bias": "model-00003-of-00003.safetensors",
563
+ "ts_encoder.layers.2.var_att_block.attn_var.proj.weight": "model-00003-of-00003.safetensors",
564
+ "ts_encoder.layers.2.var_att_block.attn_var.qkv.bias": "model-00003-of-00003.safetensors",
565
+ "ts_encoder.layers.2.var_att_block.attn_var.qkv.weight": "model-00003-of-00003.safetensors",
566
+ "ts_encoder.layers.2.var_att_block.norm1.bias": "model-00003-of-00003.safetensors",
567
+ "ts_encoder.layers.2.var_att_block.norm1.weight": "model-00003-of-00003.safetensors",
568
+ "ts_encoder.layers.3.feed_forward.fc1.bias": "model-00003-of-00003.safetensors",
569
+ "ts_encoder.layers.3.feed_forward.fc1.weight": "model-00003-of-00003.safetensors",
570
+ "ts_encoder.layers.3.feed_forward.fc2.bias": "model-00003-of-00003.safetensors",
571
+ "ts_encoder.layers.3.feed_forward.fc2.weight": "model-00003-of-00003.safetensors",
572
+ "ts_encoder.layers.3.seq_att_block.attn_seq.proj.bias": "model-00003-of-00003.safetensors",
573
+ "ts_encoder.layers.3.seq_att_block.attn_seq.proj.weight": "model-00003-of-00003.safetensors",
574
+ "ts_encoder.layers.3.seq_att_block.attn_seq.qkv.bias": "model-00003-of-00003.safetensors",
575
+ "ts_encoder.layers.3.seq_att_block.attn_seq.qkv.weight": "model-00003-of-00003.safetensors",
576
+ "ts_encoder.layers.3.seq_att_block.norm1.bias": "model-00003-of-00003.safetensors",
577
+ "ts_encoder.layers.3.seq_att_block.norm1.weight": "model-00003-of-00003.safetensors",
578
+ "ts_encoder.layers.3.var_att_block.attn_var.proj.bias": "model-00003-of-00003.safetensors",
579
+ "ts_encoder.layers.3.var_att_block.attn_var.proj.weight": "model-00003-of-00003.safetensors",
580
+ "ts_encoder.layers.3.var_att_block.attn_var.qkv.bias": "model-00003-of-00003.safetensors",
581
+ "ts_encoder.layers.3.var_att_block.attn_var.qkv.weight": "model-00003-of-00003.safetensors",
582
+ "ts_encoder.layers.3.var_att_block.norm1.bias": "model-00003-of-00003.safetensors",
583
+ "ts_encoder.layers.3.var_att_block.norm1.weight": "model-00003-of-00003.safetensors",
584
+ "ts_encoder.norm.bias": "model-00003-of-00003.safetensors",
585
+ "ts_encoder.norm.weight": "model-00003-of-00003.safetensors",
586
+ "ts_encoder.patch_embedding.0.weight": "model-00003-of-00003.safetensors",
587
+ "ts_encoder.proj_head.bias": "model-00003-of-00003.safetensors",
588
+ "ts_encoder.proj_head.weight": "model-00003-of-00003.safetensors",
589
+ "ts_project.bias": "model-00003-of-00003.safetensors",
590
+ "ts_project.weight": "model-00003-of-00003.safetensors"
591
+ }
592
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a07b9ee02f52222c67501d56b94377aae5a3ca03bd1ad56d15f64b53c355654c
3
+ size 416392314
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c226e920f7d4932425010a19e164f37be55cb7c4cb0bf0b427cd9f031d0a891e
3
+ size 15024
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e16477fddd45b0bafa84d15188ff67c94a3fd2dd469cf63669bd645d819d58a
3
+ size 15024
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c85fc0a1b0ce5a407e5e93a3dcf8fb5fb7446041945f648eec6721c4b0040e4f
3
+ size 15024
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c2359cd626bfccb24bca628b7a3560cbccba6db07ec284f6b9e2abfcf14a8e
3
+ size 15024
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f47fca151be91263d1d9a0c0fdaf9b2e5926fcfad8ea17ea0f150d5b79e559
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a8fcd189ebb7f0c0b5d836a0038a06455e078443087501ffcaa9e865ee5c4b6
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
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": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
trainer_state.json ADDED
@@ -0,0 +1,622 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 300000000000000000,
7
+ "global_step": 4230,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02364066193853428,
14
+ "grad_norm": 4265.77734375,
15
+ "learning_rate": 2.695035460992908e-06,
16
+ "loss": 19.7865,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.04728132387706856,
21
+ "grad_norm": Infinity,
22
+ "learning_rate": 6.2411347517730495e-06,
23
+ "loss": 9.5661,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.07092198581560284,
28
+ "grad_norm": 1082.762939453125,
29
+ "learning_rate": 9.645390070921986e-06,
30
+ "loss": 2.3602,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.09456264775413711,
35
+ "grad_norm": 249.59776306152344,
36
+ "learning_rate": 1.3191489361702129e-05,
37
+ "loss": 1.7304,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.1182033096926714,
42
+ "grad_norm": 171.15611267089844,
43
+ "learning_rate": 1.673758865248227e-05,
44
+ "loss": 1.6707,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.14184397163120568,
49
+ "grad_norm": 64.97687530517578,
50
+ "learning_rate": 2.028368794326241e-05,
51
+ "loss": 1.5563,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.16548463356973994,
56
+ "grad_norm": 22.22820472717285,
57
+ "learning_rate": 2.3829787234042553e-05,
58
+ "loss": 1.4809,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.18912529550827423,
63
+ "grad_norm": 17.94223403930664,
64
+ "learning_rate": 2.7375886524822697e-05,
65
+ "loss": 1.3877,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.2127659574468085,
70
+ "grad_norm": 6.133880615234375,
71
+ "learning_rate": 2.999913686685402e-05,
72
+ "loss": 1.2877,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.2364066193853428,
77
+ "grad_norm": 5.359964370727539,
78
+ "learning_rate": 2.9979733510221677e-05,
79
+ "loss": 1.1985,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.26004728132387706,
84
+ "grad_norm": 8.637283325195312,
85
+ "learning_rate": 2.9934831545542617e-05,
86
+ "loss": 1.1513,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.28368794326241137,
91
+ "grad_norm": 13.667312622070312,
92
+ "learning_rate": 2.986450740525784e-05,
93
+ "loss": 1.0896,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.3073286052009456,
98
+ "grad_norm": 6.358010292053223,
99
+ "learning_rate": 2.9768880795615002e-05,
100
+ "loss": 1.0343,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.3309692671394799,
105
+ "grad_norm": 4.579405784606934,
106
+ "learning_rate": 2.9648114492903583e-05,
107
+ "loss": 0.9778,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.3546099290780142,
112
+ "grad_norm": 4.688839435577393,
113
+ "learning_rate": 2.950241406637593e-05,
114
+ "loss": 0.9688,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.37825059101654845,
119
+ "grad_norm": 5.001623153686523,
120
+ "learning_rate": 2.9332027528325834e-05,
121
+ "loss": 0.9246,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.40189125295508277,
126
+ "grad_norm": 5.845919609069824,
127
+ "learning_rate": 2.9137244911920255e-05,
128
+ "loss": 0.9075,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.425531914893617,
133
+ "grad_norm": 6.357454299926758,
134
+ "learning_rate": 2.891839777750281e-05,
135
+ "loss": 0.9032,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.4491725768321513,
140
+ "grad_norm": 4.689474105834961,
141
+ "learning_rate": 2.8675858648209442e-05,
142
+ "loss": 0.8833,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.4728132387706856,
147
+ "grad_norm": 5.220682621002197,
148
+ "learning_rate": 2.841004037585688e-05,
149
+ "loss": 0.8512,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.49645390070921985,
154
+ "grad_norm": 6.682931423187256,
155
+ "learning_rate": 2.8121395438183372e-05,
156
+ "loss": 0.8526,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.5200945626477541,
161
+ "grad_norm": 5.913801670074463,
162
+ "learning_rate": 2.7810415168637912e-05,
163
+ "loss": 0.8187,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.5437352245862884,
168
+ "grad_norm": 5.719775676727295,
169
+ "learning_rate": 2.7477628920028935e-05,
170
+ "loss": 0.8174,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.5673758865248227,
175
+ "grad_norm": 7.033783912658691,
176
+ "learning_rate": 2.712360316345627e-05,
177
+ "loss": 0.8378,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.5910165484633569,
182
+ "grad_norm": 10.351150512695312,
183
+ "learning_rate": 2.6748940524060027e-05,
184
+ "loss": 0.81,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.6146572104018913,
189
+ "grad_norm": 6.334929466247559,
190
+ "learning_rate": 2.6354278755227802e-05,
191
+ "loss": 0.8019,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.6382978723404256,
196
+ "grad_norm": 4.533697605133057,
197
+ "learning_rate": 2.5940289653006427e-05,
198
+ "loss": 0.7874,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.6619385342789598,
203
+ "grad_norm": 5.18574857711792,
204
+ "learning_rate": 2.550767791256593e-05,
205
+ "loss": 0.7758,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.6855791962174941,
210
+ "grad_norm": 5.3152923583984375,
211
+ "learning_rate": 2.5057179928662506e-05,
212
+ "loss": 0.7811,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.7092198581560284,
217
+ "grad_norm": 6.021467685699463,
218
+ "learning_rate": 2.458956254214211e-05,
219
+ "loss": 0.7849,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.7328605200945626,
224
+ "grad_norm": 9.204541206359863,
225
+ "learning_rate": 2.4105621734618613e-05,
226
+ "loss": 0.7653,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.7565011820330969,
231
+ "grad_norm": 7.0010504722595215,
232
+ "learning_rate": 2.3606181273548253e-05,
233
+ "loss": 0.7578,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.7801418439716312,
238
+ "grad_norm": 4.713606357574463,
239
+ "learning_rate": 2.309209131000687e-05,
240
+ "loss": 0.743,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.8037825059101655,
245
+ "grad_norm": 8.350544929504395,
246
+ "learning_rate": 2.256422693155675e-05,
247
+ "loss": 0.7327,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.8274231678486997,
252
+ "grad_norm": 5.2699713706970215,
253
+ "learning_rate": 2.2023486672666385e-05,
254
+ "loss": 0.7252,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.851063829787234,
259
+ "grad_norm": 5.1293625831604,
260
+ "learning_rate": 2.1470790985218804e-05,
261
+ "loss": 0.7169,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.8747044917257684,
266
+ "grad_norm": 5.4763407707214355,
267
+ "learning_rate": 2.0907080671711832e-05,
268
+ "loss": 0.7208,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.8983451536643026,
273
+ "grad_norm": 13.955887794494629,
274
+ "learning_rate": 2.0333315283817486e-05,
275
+ "loss": 0.7309,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.9219858156028369,
280
+ "grad_norm": 8.627326011657715,
281
+ "learning_rate": 1.975047148902632e-05,
282
+ "loss": 0.7155,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.9456264775413712,
287
+ "grad_norm": 8.94743537902832,
288
+ "learning_rate": 1.9159541408157158e-05,
289
+ "loss": 0.7068,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.9692671394799054,
294
+ "grad_norm": 5.135090351104736,
295
+ "learning_rate": 1.8561530926562023e-05,
296
+ "loss": 0.6918,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.9929078014184397,
301
+ "grad_norm": 38.368629455566406,
302
+ "learning_rate": 1.795745798190099e-05,
303
+ "loss": 0.6818,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 1.016548463356974,
308
+ "grad_norm": 25.27336311340332,
309
+ "learning_rate": 1.734835083140153e-05,
310
+ "loss": 0.685,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 1.0401891252955082,
315
+ "grad_norm": 7.319797992706299,
316
+ "learning_rate": 1.6735246301551825e-05,
317
+ "loss": 0.6739,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 1.0638297872340425,
322
+ "grad_norm": 10.93574333190918,
323
+ "learning_rate": 1.6119188023207348e-05,
324
+ "loss": 0.6828,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 1.0874704491725768,
329
+ "grad_norm": 51.116207122802734,
330
+ "learning_rate": 1.5501224655115118e-05,
331
+ "loss": 0.6514,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 1.1111111111111112,
336
+ "grad_norm": 17.643468856811523,
337
+ "learning_rate": 1.4882408098879367e-05,
338
+ "loss": 0.6708,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 1.1347517730496455,
343
+ "grad_norm": 24.42500114440918,
344
+ "learning_rate": 1.426379170840718e-05,
345
+ "loss": 0.6595,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 1.1583924349881798,
350
+ "grad_norm": 7.433150291442871,
351
+ "learning_rate": 1.364642849688209e-05,
352
+ "loss": 0.6545,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 1.1820330969267139,
357
+ "grad_norm": 12.09028148651123,
358
+ "learning_rate": 1.3031369344317569e-05,
359
+ "loss": 0.6533,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 1.2056737588652482,
364
+ "grad_norm": 8.16505241394043,
365
+ "learning_rate": 1.2419661208741687e-05,
366
+ "loss": 0.6466,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 1.2293144208037825,
371
+ "grad_norm": 8.545854568481445,
372
+ "learning_rate": 1.181234534405775e-05,
373
+ "loss": 0.6311,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 1.2529550827423168,
378
+ "grad_norm": 7.951985836029053,
379
+ "learning_rate": 1.1210455527614574e-05,
380
+ "loss": 0.6338,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 1.2765957446808511,
385
+ "grad_norm": 17.269718170166016,
386
+ "learning_rate": 1.061501630050338e-05,
387
+ "loss": 0.6214,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 1.3002364066193852,
392
+ "grad_norm": 14.052486419677734,
393
+ "learning_rate": 1.0027041223576735e-05,
394
+ "loss": 0.6307,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 1.3238770685579198,
399
+ "grad_norm": 7.13311767578125,
400
+ "learning_rate": 9.447531152158089e-06,
401
+ "loss": 0.6273,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 1.3475177304964538,
406
+ "grad_norm": 9.32107162475586,
407
+ "learning_rate": 8.877472532378836e-06,
408
+ "loss": 0.6218,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 1.3711583924349882,
413
+ "grad_norm": 6.4954118728637695,
414
+ "learning_rate": 8.317835722042693e-06,
415
+ "loss": 0.6085,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 1.3947990543735225,
420
+ "grad_norm": 7.570118427276611,
421
+ "learning_rate": 7.769573338875851e-06,
422
+ "loss": 0.6007,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 1.4184397163120568,
427
+ "grad_norm": 18.045612335205078,
428
+ "learning_rate": 7.2336186389743095e-06,
429
+ "loss": 0.6177,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 1.442080378250591,
434
+ "grad_norm": 10.485590934753418,
435
+ "learning_rate": 6.710883928208835e-06,
436
+ "loss": 0.5859,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 1.4657210401891252,
441
+ "grad_norm": 13.521890640258789,
442
+ "learning_rate": 6.202259009291401e-06,
443
+ "loss": 0.6117,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 1.4893617021276595,
448
+ "grad_norm": 10.763672828674316,
449
+ "learning_rate": 5.708609667146788e-06,
450
+ "loss": 0.5647,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 1.5130023640661938,
455
+ "grad_norm": 13.315629959106445,
456
+ "learning_rate": 5.2307761951673425e-06,
457
+ "loss": 0.6115,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 1.5366430260047281,
462
+ "grad_norm": 13.952415466308594,
463
+ "learning_rate": 4.769571964859664e-06,
464
+ "loss": 0.594,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 1.5602836879432624,
469
+ "grad_norm": 9.341636657714844,
470
+ "learning_rate": 4.325782041317874e-06,
471
+ "loss": 0.5803,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 1.5839243498817965,
476
+ "grad_norm": 23.52338218688965,
477
+ "learning_rate": 3.900161846880281e-06,
478
+ "loss": 0.5648,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 1.607565011820331,
483
+ "grad_norm": 22.669052124023438,
484
+ "learning_rate": 3.4934358752441315e-06,
485
+ "loss": 0.5588,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 1.6312056737588652,
490
+ "grad_norm": 50.38961410522461,
491
+ "learning_rate": 3.106296458227363e-06,
492
+ "loss": 0.5777,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 1.6548463356973995,
497
+ "grad_norm": 6.503214359283447,
498
+ "learning_rate": 2.7394025872764556e-06,
499
+ "loss": 0.5688,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 1.6784869976359338,
504
+ "grad_norm": 81.57908630371094,
505
+ "learning_rate": 2.39337879172658e-06,
506
+ "loss": 0.5849,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 1.702127659574468,
511
+ "grad_norm": 10.680161476135254,
512
+ "learning_rate": 2.0688140757233428e-06,
513
+ "loss": 0.5761,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 1.7257683215130024,
518
+ "grad_norm": 6.659136772155762,
519
+ "learning_rate": 1.7662609156157749e-06,
520
+ "loss": 0.566,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 1.7494089834515365,
525
+ "grad_norm": 13.552983283996582,
526
+ "learning_rate": 1.486234319527186e-06,
527
+ "loss": 0.5625,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 1.773049645390071,
532
+ "grad_norm": 22.759199142456055,
533
+ "learning_rate": 1.2292109507047273e-06,
534
+ "loss": 0.557,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 1.7966903073286051,
539
+ "grad_norm": 36.262474060058594,
540
+ "learning_rate": 9.956283161398172e-07,
541
+ "loss": 0.5561,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 1.8203309692671394,
546
+ "grad_norm": 8.722681999206543,
547
+ "learning_rate": 7.858840218406921e-07,
548
+ "loss": 0.5624,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 1.8439716312056738,
553
+ "grad_norm": 6.087028980255127,
554
+ "learning_rate": 6.00335096024619e-07,
555
+ "loss": 0.5747,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 1.867612293144208,
560
+ "grad_norm": 9.753291130065918,
561
+ "learning_rate": 4.3929738138196787e-07,
562
+ "loss": 0.5629,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 1.8912529550827424,
567
+ "grad_norm": 13.233976364135742,
568
+ "learning_rate": 3.030449974465471e-07,
569
+ "loss": 0.5588,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 1.9148936170212765,
574
+ "grad_norm": 23.338430404663086,
575
+ "learning_rate": 1.9180987398740358e-07,
576
+ "loss": 0.5632,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 1.938534278959811,
581
+ "grad_norm": 30.731971740722656,
582
+ "learning_rate": 1.0578135621633178e-07,
583
+ "loss": 0.5566,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 1.962174940898345,
588
+ "grad_norm": 12.004512786865234,
589
+ "learning_rate": 4.5105882483119643e-08,
590
+ "loss": 0.5446,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 1.9858156028368794,
595
+ "grad_norm": 18.55535125732422,
596
+ "learning_rate": 9.886735007152425e-09,
597
+ "loss": 0.5539,
598
+ "step": 4200
599
+ }
600
+ ],
601
+ "logging_steps": 50,
602
+ "max_steps": 4230,
603
+ "num_input_tokens_seen": 0,
604
+ "num_train_epochs": 2,
605
+ "save_steps": 1000,
606
+ "stateful_callbacks": {
607
+ "TrainerControl": {
608
+ "args": {
609
+ "should_epoch_stop": false,
610
+ "should_evaluate": false,
611
+ "should_log": false,
612
+ "should_save": true,
613
+ "should_training_stop": true
614
+ },
615
+ "attributes": {}
616
+ }
617
+ },
618
+ "total_flos": 4.480992965002527e+17,
619
+ "train_batch_size": 12,
620
+ "trial_name": null,
621
+ "trial_params": null
622
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42ce438d1ce818ae519b0ad36a9bf5578b08b73796e3f667ec9207f83a5439a
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff