Hugging Face's logo

Montalte
/
qwen3_0.6b_opencode

Safetensors
qwen3
Model card Files
xet
 Community
Montalte commited on
Commit
0b24cd2
·
verified ·
1 Parent(s): 77af52a

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +85 -0
  3. config.json +63 -0
  4. generation_config.json +10 -0
  5. model.safetensors +3 -0
  6. optimizer.pt +3 -0
  7. rng_state_0.pth +3 -0
  8. rng_state_1.pth +3 -0
  9. rng_state_2.pth +3 -0
  10. rng_state_3.pth +3 -0
  11. scheduler.pt +3 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +30 -0
  14. trainer_state.json +188 -0
  15. 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 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# 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>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\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" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
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
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 32768,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "pad_token_id": 151643,
52
+ "rms_norm_eps": 1e-06,
53
+ "rope_parameters": {
54
+ "rope_theta": 1000000,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_window": null,
58
+ "tie_word_embeddings": true,
59
+ "transformers_version": "5.2.0",
60
+ "use_cache": false,
61
+ "use_sliding_window": false,
62
+ "vocab_size": 151936
63
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": false,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "max_new_tokens": 2048,
8
+ "pad_token_id": 151643,
9
+ "transformers_version": "5.2.0"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f3dd11244986b823d5d2466eac15c81f9b6e047d59626f90edd31537e3c737
3
+ size 2384234968
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af0d221a51684f223a1bd686517d0d63adbf5ff3e8b647dfa9e736c4116695c1
3
+ size 4768669395
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c213a373f3e5d95993ad095a3790a902d821a1b4b93a10cc7d382c8726fcb9d
3
+ size 15429
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb125336725f7741cb4daa1e3d06e225bbacfde8d41c4dcabb6762c222e62c6
3
+ size 15429
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:153c865f77c7129ba565bded50f334683d51c80f20e3cfec39e62f8737b86f0d
3
+ size 15429
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d017ce00fcebac7edc058ddd138f194eb0340f2d8ad0879bdab08f922ed0846e
3
+ size 15429
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b2b5072c8b2d8aedeffbe6e5d3b5c704b67d5610d59ad55de2fbc822578341
3
+ size 1465
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
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
+ "model_max_length": 131072,
25
+ "pad_token": "<|endoftext|>",
26
+ "padding_side": "right",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }
trainer_state.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 200,
7
+ "global_step": 225,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.13468013468013468,
14
+ "grad_norm": 0.31015893816947937,
15
+ "learning_rate": 1.5000000000000002e-05,
16
+ "loss": 0.38761081695556643,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.26936026936026936,
21
+ "grad_norm": 0.21577006578445435,
22
+ "learning_rate": 1.9946749853292233e-05,
23
+ "loss": 0.3502843379974365,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.40404040404040403,
28
+ "grad_norm": 0.22367797791957855,
29
+ "learning_rate": 1.9687297122400952e-05,
30
+ "loss": 0.3208463191986084,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.5387205387205387,
35
+ "grad_norm": 0.20365038514137268,
36
+ "learning_rate": 1.9217488001088784e-05,
37
+ "loss": 0.3184423685073853,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.6734006734006734,
42
+ "grad_norm": 0.2231130301952362,
43
+ "learning_rate": 1.8547524236003675e-05,
44
+ "loss": 0.3126647472381592,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.8080808080808081,
49
+ "grad_norm": 0.209013894200325,
50
+ "learning_rate": 1.7691953864390208e-05,
51
+ "loss": 0.3156299591064453,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.9427609427609428,
56
+ "grad_norm": 0.1777929961681366,
57
+ "learning_rate": 1.666935530836651e-05,
58
+ "loss": 0.2766378402709961,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.0673400673400673,
63
+ "grad_norm": 0.17185629904270172,
64
+ "learning_rate": 1.5501933950752655e-05,
65
+ "loss": 0.24300642013549806,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 1.202020202020202,
70
+ "grad_norm": 0.18560396134853363,
71
+ "learning_rate": 1.4215039952670482e-05,
72
+ "loss": 0.20093803405761718,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 1.3367003367003367,
77
+ "grad_norm": 0.17960919439792633,
78
+ "learning_rate": 1.2836617783342968e-05,
79
+ "loss": 0.19915937185287474,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 1.4713804713804715,
84
+ "grad_norm": 0.17622533440589905,
85
+ "learning_rate": 1.1396599415368062e-05,
86
+ "loss": 0.19454092979431153,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 1.606060606060606,
91
+ "grad_norm": 0.1789940446615219,
92
+ "learning_rate": 9.926254362026875e-06,
93
+ "loss": 0.19552748203277587,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 1.7407407407407407,
98
+ "grad_norm": 0.1863929182291031,
99
+ "learning_rate": 8.457510670346976e-06,
100
+ "loss": 0.19949347972869874,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 1.8754208754208754,
105
+ "grad_norm": 0.16495266556739807,
106
+ "learning_rate": 7.022261614327448e-06,
107
+ "loss": 0.20035164356231688,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 2.0,
112
+ "grad_norm": 0.3942849636077881,
113
+ "learning_rate": 5.651673143248509e-06,
114
+ "loss": 0.19270834922790528,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 2.1346801346801345,
119
+ "grad_norm": 0.17539165914058685,
120
+ "learning_rate": 4.375507123592194e-06,
121
+ "loss": 0.1418288230895996,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 2.2693602693602695,
126
+ "grad_norm": 0.18225708603858948,
127
+ "learning_rate": 3.2214750701474875e-06,
128
+ "loss": 0.13898892402648927,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 2.404040404040404,
133
+ "grad_norm": 0.172335684299469,
134
+ "learning_rate": 2.2146363998111077e-06,
135
+ "loss": 0.14039983749389648,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 2.538720538720539,
140
+ "grad_norm": 0.1543879359960556,
141
+ "learning_rate": 1.3768542747997215e-06,
142
+ "loss": 0.13042680025100709,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 2.6734006734006734,
147
+ "grad_norm": 0.16937494277954102,
148
+ "learning_rate": 7.263208514547548e-07,
149
+ "loss": 0.12810491323471068,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 2.808080808080808,
154
+ "grad_norm": 0.17165407538414001,
155
+ "learning_rate": 2.7716224370188836e-07,
156
+ "loss": 0.1331431746482849,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 2.942760942760943,
161
+ "grad_norm": 0.14236703515052795,
162
+ "learning_rate": 3.913177925055189e-08,
163
+ "loss": 0.12828856706619263,
164
+ "step": 220
165
+ }
166
+ ],
167
+ "logging_steps": 10,
168
+ "max_steps": 225,
169
+ "num_input_tokens_seen": 0,
170
+ "num_train_epochs": 3,
171
+ "save_steps": 200,
172
+ "stateful_callbacks": {
173
+ "TrainerControl": {
174
+ "args": {
175
+ "should_epoch_stop": false,
176
+ "should_evaluate": false,
177
+ "should_log": false,
178
+ "should_save": true,
179
+ "should_training_stop": true
180
+ },
181
+ "attributes": {}
182
+ }
183
+ },
184
+ "total_flos": 2.2113763633135616e+16,
185
+ "train_batch_size": 2,
186
+ "trial_name": null,
187
+ "trial_params": null
188
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6c2eaa9bbc614f38bb9907adf820c7e375a209995fab0c7e25acd197676330
3
+ size 5585