Hugging Face's logo

XaiverZ
/
MemPilot-4B

Safetensors
Model card Files
xet
 Community
XaiverZ commited on
Commit
583fd38
·
verified ·
1 Parent(s): 372e66b

Remove incorrect cost-first files

Browse files
Files changed (22) hide show
  1. cost-first/global_step_351/actor/extra_state_world_size_4_rank_0.pt +0 -3
  2. cost-first/global_step_351/actor/extra_state_world_size_4_rank_1.pt +0 -3
  3. cost-first/global_step_351/actor/extra_state_world_size_4_rank_2.pt +0 -3
  4. cost-first/global_step_351/actor/extra_state_world_size_4_rank_3.pt +0 -3
  5. cost-first/global_step_351/actor/fsdp_config.json +0 -4
  6. cost-first/global_step_351/actor/huggingface/added_tokens.json +0 -28
  7. cost-first/global_step_351/actor/huggingface/chat_template.jinja +0 -61
  8. cost-first/global_step_351/actor/huggingface/config.json +0 -68
  9. cost-first/global_step_351/actor/huggingface/generation_config.json +0 -13
  10. cost-first/global_step_351/actor/huggingface/merges.txt +0 -0
  11. cost-first/global_step_351/actor/huggingface/special_tokens_map.json +0 -31
  12. cost-first/global_step_351/actor/huggingface/tokenizer.json +0 -3
  13. cost-first/global_step_351/actor/huggingface/tokenizer_config.json +0 -239
  14. cost-first/global_step_351/actor/huggingface/vocab.json +0 -0
  15. cost-first/global_step_351/actor/model_world_size_4_rank_0.pt +0 -3
  16. cost-first/global_step_351/actor/model_world_size_4_rank_1.pt +0 -3
  17. cost-first/global_step_351/actor/model_world_size_4_rank_2.pt +0 -3
  18. cost-first/global_step_351/actor/model_world_size_4_rank_3.pt +0 -3
  19. cost-first/global_step_351/actor/optim_world_size_4_rank_0.pt +0 -3
  20. cost-first/global_step_351/actor/optim_world_size_4_rank_1.pt +0 -3
  21. cost-first/global_step_351/actor/optim_world_size_4_rank_2.pt +0 -3
  22. cost-first/global_step_351/actor/optim_world_size_4_rank_3.pt +0 -3
cost-first/global_step_351/actor/extra_state_world_size_4_rank_0.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:067035c55f13c31ad2d1743b45b1cf7b132c970cdd5af2e895358ee25c73cc3b
3
- size 15141
 
 
 
 
cost-first/global_step_351/actor/extra_state_world_size_4_rank_1.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d91abc54070c26c17ba48a9587fd470d1e6b966a61e6d1d9c46566fe75e77acd
3
- size 15077
 
 
 
 
cost-first/global_step_351/actor/extra_state_world_size_4_rank_2.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c600ead07238c1d631544c7102f5db96f13c93bf48a062fd73fd36f4e90b3841
3
- size 15141
 
 
 
 
cost-first/global_step_351/actor/extra_state_world_size_4_rank_3.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eee3cceafc8769be7f64b710ae08b3a743dd91b50f8ae797b6afd7cfdfbb0119
3
- size 15141
 
 
 
 
cost-first/global_step_351/actor/fsdp_config.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "FSDP_version": 1,
3
- "world_size": 4
4
- }
 
 
 
 
 
cost-first/global_step_351/actor/huggingface/added_tokens.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cost-first/global_step_351/actor/huggingface/chat_template.jinja DELETED
@@ -1,61 +0,0 @@
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
- {%- for message in messages %}
18
- {%- if message.content is string %}
19
- {%- set content = message.content %}
20
- {%- else %}
21
- {%- set content = '' %}
22
- {%- endif %}
23
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
- {%- elif message.role == "assistant" %}
26
- {{- '<|im_start|>' + message.role + '\n' + content }}
27
- {%- if message.tool_calls %}
28
- {%- for tool_call in message.tool_calls %}
29
- {%- if (loop.first and content) or (not loop.first) %}
30
- {{- '\n' }}
31
- {%- endif %}
32
- {%- if tool_call.function %}
33
- {%- set tool_call = tool_call.function %}
34
- {%- endif %}
35
- {{- '<tool_call>\n{"name": "' }}
36
- {{- tool_call.name }}
37
- {{- '", "arguments": ' }}
38
- {%- if tool_call.arguments is string %}
39
- {{- tool_call.arguments }}
40
- {%- else %}
41
- {{- tool_call.arguments | tojson }}
42
- {%- endif %}
43
- {{- '}\n</tool_call>' }}
44
- {%- endfor %}
45
- {%- endif %}
46
- {{- '<|im_end|>\n' }}
47
- {%- elif message.role == "tool" %}
48
- {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
49
- {{- '<|im_start|>user' }}
50
- {%- endif %}
51
- {{- '\n<tool_response>\n' }}
52
- {{- content }}
53
- {{- '\n</tool_response>' }}
54
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
55
- {{- '<|im_end|>\n' }}
56
- {%- endif %}
57
- {%- endif %}
58
- {%- endfor %}
59
- {%- if add_generation_prompt %}
60
- {{- '<|im_start|>assistant\n' }}
61
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cost-first/global_step_351/actor/huggingface/config.json DELETED
@@ -1,68 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "dtype": "float32",
8
- "eos_token_id": 151645,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
- "hidden_size": 2560,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 9728,
14
- "layer_types": [
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
- "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
- ],
52
- "max_position_embeddings": 262144,
53
- "max_window_layers": 36,
54
- "model_type": "qwen3",
55
- "num_attention_heads": 32,
56
- "num_hidden_layers": 36,
57
- "num_key_value_heads": 8,
58
- "pad_token_id": 151643,
59
- "rms_norm_eps": 1e-06,
60
- "rope_scaling": null,
61
- "rope_theta": 5000000,
62
- "sliding_window": null,
63
- "tie_word_embeddings": true,
64
- "transformers_version": "4.57.6",
65
- "use_cache": true,
66
- "use_sliding_window": false,
67
- "vocab_size": 151936
68
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cost-first/global_step_351/actor/huggingface/generation_config.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "temperature": 0.7,
10
- "top_k": 20,
11
- "top_p": 0.8,
12
- "transformers_version": "4.57.6"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cost-first/global_step_351/actor/huggingface/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
cost-first/global_step_351/actor/huggingface/special_tokens_map.json DELETED
@@ -1,31 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cost-first/global_step_351/actor/huggingface/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654
 
 
 
 
cost-first/global_step_351/actor/huggingface/tokenizer_config.json DELETED
@@ -1,239 +0,0 @@
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
- "151665": {
182
- "content": "<tool_response>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "151666": {
190
- "content": "</tool_response>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "151667": {
198
- "content": "<think>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "151668": {
206
- "content": "</think>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|im_start|>",
216
- "<|im_end|>",
217
- "<|object_ref_start|>",
218
- "<|object_ref_end|>",
219
- "<|box_start|>",
220
- "<|box_end|>",
221
- "<|quad_start|>",
222
- "<|quad_end|>",
223
- "<|vision_start|>",
224
- "<|vision_end|>",
225
- "<|vision_pad|>",
226
- "<|image_pad|>",
227
- "<|video_pad|>"
228
- ],
229
- "bos_token": null,
230
- "clean_up_tokenization_spaces": false,
231
- "eos_token": "<|im_end|>",
232
- "errors": "replace",
233
- "extra_special_tokens": {},
234
- "model_max_length": 1010000,
235
- "pad_token": "<|endoftext|>",
236
- "split_special_tokens": false,
237
- "tokenizer_class": "Qwen2Tokenizer",
238
- "unk_token": null
239
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cost-first/global_step_351/actor/huggingface/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
cost-first/global_step_351/actor/model_world_size_4_rank_0.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7477d6e01851871bcec299d690d34cce5d7f05b29fd5ae27fa61dcf592614ee5
3
- size 4411655819
 
 
 
 
cost-first/global_step_351/actor/model_world_size_4_rank_1.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b014f0c921b6bd03470f97326c2d660e56782129f5c718113547de0ddbd15e33
3
- size 4411655819
 
 
 
 
cost-first/global_step_351/actor/model_world_size_4_rank_2.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:03c5077eb1786cf4174d5e260c335cf62d07e29ae48601f8a605fe62077d1fc2
3
- size 4411655819
 
 
 
 
cost-first/global_step_351/actor/model_world_size_4_rank_3.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:509ff7c42720cd90e96ef747c79e71599237256f664541a9688f840353a5cbf3
3
- size 4411655819
 
 
 
 
cost-first/global_step_351/actor/optim_world_size_4_rank_0.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f333cc54cbc01f126968679b66abc4e837a2d2616291d7ec3c95c17350f188f
3
- size 8044970575
 
 
 
 
cost-first/global_step_351/actor/optim_world_size_4_rank_1.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:021ff82e5775bfb0d993a24bed185102a2225c39eaa5bee156e3a915018e9bec
3
- size 8044970575
 
 
 
 
cost-first/global_step_351/actor/optim_world_size_4_rank_2.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:60391caa566717b39175d1b6bc1992069523094fe019c3de1fee5d3742b12837
3
- size 8044970575
 
 
 
 
cost-first/global_step_351/actor/optim_world_size_4_rank_3.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0988e5c179dac982dcf54ae622a11044c2c1204d225e245baa12a93bdfcfabc5
3
- size 8044970575