Hugging Face's logo

DatPySci
/
knowledge-context-distillation

Safetensors
Model card Files
xet
 Community
DatPySci commited on
Commit
c6c6fd5
·
verified ·
1 Parent(s): f3ceb18

Delete DeepSeek-R1-0528-Qwen3-8B-m23k-SFT

Browse files
Files changed (11) hide show
  1. DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/data.pt +0 -3
  2. DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/extra_state_world_size_2_rank_0.pt +0 -3
  3. DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/extra_state_world_size_2_rank_1.pt +0 -3
  4. DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/fsdp_config.json +0 -4
  5. DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/huggingface/chat_template.jinja +0 -14
  6. DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/huggingface/config.json +0 -73
  7. DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/huggingface/special_tokens_map.json +0 -23
  8. DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/huggingface/tokenizer.json +0 -3
  9. DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/huggingface/tokenizer_config.json +0 -242
  10. DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/model_world_size_2_rank_0.pt +0 -3
  11. DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/model_world_size_2_rank_1.pt +0 -3
DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/data.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1fceb7958990c0c8dd21df4585c76fe94547823222769be48dd6694b0891880
3
- size 1947
 
 
 
 
DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/extra_state_world_size_2_rank_0.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:714efd0ebc36705750a530a52a738ee321bcc102a76b717520cb66fa003ca5c3
3
- size 15205
 
 
 
 
DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/extra_state_world_size_2_rank_1.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b08417c41a846eba3498859c7f1a73434eee6e1c423158a8380ba63bfc6dfef3
3
- size 15205
 
 
 
 
DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/fsdp_config.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "FSDP_version": 2,
3
- "world_size": 2
4
- }
 
 
 
 
 
DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/huggingface/chat_template.jinja DELETED
@@ -1,14 +0,0 @@
1
- {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '
2
-
3
- ' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + content + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
4
- ' + '```json' + '
5
- ' + tool['function']['arguments'] + '
6
- ' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
7
- ' + '```json' + '
8
- ' + tool['function']['arguments'] + '
9
- ' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'
10
- ' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
11
- ' + '```json' + '
12
- ' + tool['function']['arguments'] + '
13
- ' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'
14
- <｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/huggingface/config.json DELETED
@@ -1,73 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "dtype": "float32",
9
- "eos_token_id": 151645,
10
- "head_dim": 128,
11
- "hidden_act": "silu",
12
- "hidden_size": 4096,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 12288,
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
- "full_attention",
45
- "full_attention",
46
- "full_attention",
47
- "full_attention",
48
- "full_attention",
49
- "full_attention",
50
- "full_attention",
51
- "full_attention"
52
- ],
53
- "max_position_embeddings": 131072,
54
- "max_window_layers": 36,
55
- "model_type": "qwen3",
56
- "num_attention_heads": 32,
57
- "num_hidden_layers": 36,
58
- "num_key_value_heads": 8,
59
- "rms_norm_eps": 1e-06,
60
- "rope_scaling": {
61
- "attn_factor": 0.8782488562869419,
62
- "factor": 4.0,
63
- "original_max_position_embeddings": 32768,
64
- "rope_type": "yarn"
65
- },
66
- "rope_theta": 1000000,
67
- "sliding_window": null,
68
- "tie_word_embeddings": false,
69
- "transformers_version": "4.56.1",
70
- "use_cache": true,
71
- "use_sliding_window": false,
72
- "vocab_size": 151936
73
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/huggingface/special_tokens_map.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<｜begin▁of▁sentence｜>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<｜end▁of▁sentence｜>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<｜end▁of▁sentence｜>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/huggingface/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:93d5fd6d2f8cf1172ac86cf982e2b88fa6732366b44dc1a32349379a54a6a044
3
- size 11423346
 
 
 
 
DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/huggingface/tokenizer_config.json DELETED
@@ -1,242 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
- "added_tokens_decoder": {
6
- "151643": {
7
- "content": "<｜begin▁of▁sentence｜>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false,
12
- "special": true
13
- },
14
- "151644": {
15
- "content": "<|im_start|>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "151645": {
23
- "content": "<｜end▁of▁sentence｜>",
24
- "lstrip": false,
25
- "normalized": false,
26
- "rstrip": false,
27
- "single_word": false,
28
- "special": true
29
- },
30
- "151646": {
31
- "content": "<|object_ref_start|>",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false,
36
- "special": true
37
- },
38
- "151647": {
39
- "content": "<|object_ref_end|>",
40
- "lstrip": false,
41
- "normalized": false,
42
- "rstrip": false,
43
- "single_word": false,
44
- "special": true
45
- },
46
- "151648": {
47
- "content": "<|box_start|>",
48
- "lstrip": false,
49
- "normalized": false,
50
- "rstrip": false,
51
- "single_word": false,
52
- "special": true
53
- },
54
- "151649": {
55
- "content": "<|box_end|>",
56
- "lstrip": false,
57
- "normalized": false,
58
- "rstrip": false,
59
- "single_word": false,
60
- "special": true
61
- },
62
- "151650": {
63
- "content": "<|quad_start|>",
64
- "lstrip": false,
65
- "normalized": false,
66
- "rstrip": false,
67
- "single_word": false,
68
- "special": true
69
- },
70
- "151651": {
71
- "content": "<|quad_end|>",
72
- "lstrip": false,
73
- "normalized": false,
74
- "rstrip": false,
75
- "single_word": false,
76
- "special": true
77
- },
78
- "151652": {
79
- "content": "<|vision_start|>",
80
- "lstrip": false,
81
- "normalized": false,
82
- "rstrip": false,
83
- "single_word": false,
84
- "special": true
85
- },
86
- "151653": {
87
- "content": "<|vision_end|>",
88
- "lstrip": false,
89
- "normalized": false,
90
- "rstrip": false,
91
- "single_word": false,
92
- "special": true
93
- },
94
- "151654": {
95
- "content": "<|vision_pad|>",
96
- "lstrip": false,
97
- "normalized": false,
98
- "rstrip": false,
99
- "single_word": false,
100
- "special": true
101
- },
102
- "151655": {
103
- "content": "<|image_pad|>",
104
- "lstrip": false,
105
- "normalized": false,
106
- "rstrip": false,
107
- "single_word": false,
108
- "special": true
109
- },
110
- "151656": {
111
- "content": "<|video_pad|>",
112
- "lstrip": false,
113
- "normalized": false,
114
- "rstrip": false,
115
- "single_word": false,
116
- "special": true
117
- },
118
- "151657": {
119
- "content": "<tool_call>",
120
- "lstrip": false,
121
- "normalized": false,
122
- "rstrip": false,
123
- "single_word": false,
124
- "special": false
125
- },
126
- "151658": {
127
- "content": "</tool_call>",
128
- "lstrip": false,
129
- "normalized": false,
130
- "rstrip": false,
131
- "single_word": false,
132
- "special": false
133
- },
134
- "151659": {
135
- "content": "<|fim_prefix|>",
136
- "lstrip": false,
137
- "normalized": false,
138
- "rstrip": false,
139
- "single_word": false,
140
- "special": false
141
- },
142
- "151660": {
143
- "content": "<|fim_middle|>",
144
- "lstrip": false,
145
- "normalized": false,
146
- "rstrip": false,
147
- "single_word": false,
148
- "special": false
149
- },
150
- "151661": {
151
- "content": "<|fim_suffix|>",
152
- "lstrip": false,
153
- "normalized": false,
154
- "rstrip": false,
155
- "single_word": false,
156
- "special": false
157
- },
158
- "151662": {
159
- "content": "<|fim_pad|>",
160
- "lstrip": false,
161
- "normalized": false,
162
- "rstrip": false,
163
- "single_word": false,
164
- "special": false
165
- },
166
- "151663": {
167
- "content": "<|repo_name|>",
168
- "lstrip": false,
169
- "normalized": false,
170
- "rstrip": false,
171
- "single_word": false,
172
- "special": false
173
- },
174
- "151664": {
175
- "content": "<|file_sep|>",
176
- "lstrip": false,
177
- "normalized": false,
178
- "rstrip": false,
179
- "single_word": false,
180
- "special": false
181
- },
182
- "151665": {
183
- "content": "<tool_response>",
184
- "lstrip": false,
185
- "normalized": false,
186
- "rstrip": false,
187
- "single_word": false,
188
- "special": false
189
- },
190
- "151666": {
191
- "content": "</tool_response>",
192
- "lstrip": false,
193
- "normalized": false,
194
- "rstrip": false,
195
- "single_word": false,
196
- "special": false
197
- },
198
- "151667": {
199
- "content": "<think>",
200
- "lstrip": false,
201
- "normalized": false,
202
- "rstrip": false,
203
- "single_word": false,
204
- "special": false
205
- },
206
- "151668": {
207
- "content": "</think>",
208
- "lstrip": false,
209
- "normalized": false,
210
- "rstrip": false,
211
- "single_word": false,
212
- "special": false
213
- },
214
- "151669": {
215
- "content": "<｜User｜>",
216
- "lstrip": false,
217
- "normalized": false,
218
- "rstrip": false,
219
- "single_word": false,
220
- "special": false
221
- },
222
- "151670": {
223
- "content": "<｜Assistant｜>",
224
- "lstrip": false,
225
- "normalized": false,
226
- "rstrip": false,
227
- "single_word": false,
228
- "special": false
229
- }
230
- },
231
- "bos_token": "<｜begin▁of▁sentence｜>",
232
- "clean_up_tokenization_spaces": false,
233
- "eos_token": "<｜end▁of▁sentence｜>",
234
- "extra_special_tokens": {},
235
- "legacy": true,
236
- "model_max_length": 131072,
237
- "pad_token": "<｜end▁of▁sentence｜>",
238
- "sp_model_kwargs": {},
239
- "tokenizer_class": "LlamaTokenizerFast",
240
- "unk_token": null,
241
- "use_default_system_prompt": false
242
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/model_world_size_2_rank_0.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:93c9b31205414a8c2fb7c75dade1d0b4479380719328ae0ed2fd1e7957a9f717
3
- size 16381687787
 
 
 
 
DeepSeek-R1-0528-Qwen3-8B-m23k-SFT/model_world_size_2_rank_1.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd2447178b075feb8b8990ba17f4cfb2348965710e7591fd48d12f4bd324286e
3
- size 16381687787