Hugging Face's logo

summerMC
/
matutake

Text Generation
Transformers
Safetensors
Japanese
English
qwen2
japanese
chat
sft
causal-lm
conversational
reasoning
fable
text-generation-inference
Model card Files
xet
 Community
summerMC commited on
Commit
e22ea9a
·
verified ·
1 Parent(s): 45e66d0

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +54 -0
  3. config.json +61 -0
  4. generation_config.json +9 -0
  5. model.safetensors +3 -0
  6. optimizer.pt +3 -0
  7. rng_state.pth +3 -0
  8. scheduler.pt +3 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +30 -0
  11. trainer_state.json +124 -0
  12. training_args.bin +3 -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
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
+ {{- 'あなたは、Summer AIが開発したSakuraです。小型ながら、誠実で優秀なアシスタントです。' }}
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\nあなたは、Summer AIが開発したSakuraです。小型ながら、誠実で優秀なアシスタントです。<|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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": null,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 32768,
44
+ "max_window_layers": 21,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 2,
49
+ "pad_token_id": 151643,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "transformers_version": "5.12.0",
58
+ "use_cache": false,
59
+ "use_sliding_window": false,
60
+ "vocab_size": 151665
61
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151645
5
+ ],
6
+ "pad_token_id": 151643,
7
+ "transformers_version": "5.12.0",
8
+ "use_cache": true
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7175b36525c9067d2892388ac4785d4197057d634dcfcf2e29ccdaa87223e9e5
3
+ size 3552549728
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:401d9b863f63ad990876a15e8a2d6479a4440a9426902056b63c17a16bbece7a
3
+ size 7105319372
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac08bec92a4d36e0429c02d96598c370f748ac8366bfc29c7287da66814c605d
3
+ size 1465
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
3
+ size 11421892
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "local_files_only": false,
25
+ "model_max_length": 131072,
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }
trainer_state.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 199,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 0.9629484385251998,
14
+ "epoch": 0.10050251256281408,
15
+ "grad_norm": 4.09375,
16
+ "learning_rate": 1.9000000000000002e-06,
17
+ "loss": 0.9181639671325683,
18
+ "mean_token_accuracy": 0.8306790262460708,
19
+ "num_tokens": 40960.0,
20
+ "step": 20
21
+ },
22
+ {
23
+ "entropy": 0.9275371879339218,
24
+ "epoch": 0.20100502512562815,
25
+ "grad_norm": 4.28125,
26
+ "learning_rate": 3.900000000000001e-06,
27
+ "loss": 0.8665243148803711,
28
+ "mean_token_accuracy": 0.8379091203212738,
29
+ "num_tokens": 81920.0,
30
+ "step": 40
31
+ },
32
+ {
33
+ "entropy": 0.8652732700109482,
34
+ "epoch": 0.3015075376884422,
35
+ "grad_norm": 3.359375,
36
+ "learning_rate": 5.9e-06,
37
+ "loss": 0.7930655002593994,
38
+ "mean_token_accuracy": 0.8541035562753677,
39
+ "num_tokens": 122880.0,
40
+ "step": 60
41
+ },
42
+ {
43
+ "entropy": 0.780908739566803,
44
+ "epoch": 0.4020100502512563,
45
+ "grad_norm": 2.6875,
46
+ "learning_rate": 7.9e-06,
47
+ "loss": 0.7104530334472656,
48
+ "mean_token_accuracy": 0.8606008648872375,
49
+ "num_tokens": 163840.0,
50
+ "step": 80
51
+ },
52
+ {
53
+ "entropy": 0.598466919362545,
54
+ "epoch": 0.5025125628140703,
55
+ "grad_norm": 4.9375,
56
+ "learning_rate": 9.9e-06,
57
+ "loss": 0.5393049240112304,
58
+ "mean_token_accuracy": 0.8908646881580353,
59
+ "num_tokens": 204800.0,
60
+ "step": 100
61
+ },
62
+ {
63
+ "entropy": 0.40023221969604494,
64
+ "epoch": 0.6030150753768844,
65
+ "grad_norm": 2.734375,
66
+ "learning_rate": 9.118382907149164e-06,
67
+ "loss": 0.3737324237823486,
68
+ "mean_token_accuracy": 0.9215437412261963,
69
+ "num_tokens": 245760.0,
70
+ "step": 120
71
+ },
72
+ {
73
+ "entropy": 0.3805061921477318,
74
+ "epoch": 0.7035175879396985,
75
+ "grad_norm": 3.125,
76
+ "learning_rate": 6.635339816587109e-06,
77
+ "loss": 0.35905587673187256,
78
+ "mean_token_accuracy": 0.9224676638841629,
79
+ "num_tokens": 286652.0,
80
+ "step": 140
81
+ },
82
+ {
83
+ "entropy": 0.31945948526263235,
84
+ "epoch": 0.8040201005025126,
85
+ "grad_norm": 3.125,
86
+ "learning_rate": 3.5153981233586277e-06,
87
+ "loss": 0.29033424854278567,
88
+ "mean_token_accuracy": 0.935295569896698,
89
+ "num_tokens": 327612.0,
90
+ "step": 160
91
+ },
92
+ {
93
+ "entropy": 0.3433520093560219,
94
+ "epoch": 0.9045226130653267,
95
+ "grad_norm": 2.9375,
96
+ "learning_rate": 9.73648712344707e-07,
97
+ "loss": 0.32125253677368165,
98
+ "mean_token_accuracy": 0.930393049120903,
99
+ "num_tokens": 367708.0,
100
+ "step": 180
101
+ }
102
+ ],
103
+ "logging_steps": 20,
104
+ "max_steps": 199,
105
+ "num_input_tokens_seen": 0,
106
+ "num_train_epochs": 1,
107
+ "save_steps": 1000,
108
+ "stateful_callbacks": {
109
+ "TrainerControl": {
110
+ "args": {
111
+ "should_epoch_stop": false,
112
+ "should_evaluate": false,
113
+ "should_log": false,
114
+ "should_save": true,
115
+ "should_training_stop": true
116
+ },
117
+ "attributes": {}
118
+ }
119
+ },
120
+ "total_flos": 3757085019549696.0,
121
+ "train_batch_size": 1,
122
+ "trial_name": null,
123
+ "trial_params": null
124
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92877bd1dbb18040fd11831cbfb5c38b02d1713f51f32d02bf001e28842c0deb
3
+ size 5649