Hugging Face's logo

PhalaCloud
/
GLM-5.2-W4AFP8

Text Generation
Safetensors
English
Chinese
sglang
deepseek_v3
glm
glm_moe_dsa
mixture-of-experts
w4afp8
int4
fp8
quantized
reasoning
tool-calling
conversational
8-bit precision
Model card Files
xet
 Community
7
h4x3rotab commited on
Commit
f4af1c5
·
verified ·
1 Parent(s): 0890d4b

Add files using upload-large-folder tool

Browse files
Files changed (47) hide show
  1. .gitattributes +2 -0
  2. chat_template.jinja +119 -0
  3. config.json +229 -0
  4. model-00001-of-00040.safetensors +3 -0
  5. model-00002-of-00040.safetensors +3 -0
  6. model-00003-of-00040.safetensors +3 -0
  7. model-00004-of-00040.safetensors +3 -0
  8. model-00005-of-00040.safetensors +3 -0
  9. model-00006-of-00040.safetensors +3 -0
  10. model-00007-of-00040.safetensors +3 -0
  11. model-00008-of-00040.safetensors +3 -0
  12. model-00009-of-00040.safetensors +3 -0
  13. model-00010-of-00040.safetensors +3 -0
  14. model-00011-of-00040.safetensors +3 -0
  15. model-00012-of-00040.safetensors +3 -0
  16. model-00013-of-00040.safetensors +3 -0
  17. model-00014-of-00040.safetensors +3 -0
  18. model-00015-of-00040.safetensors +3 -0
  19. model-00016-of-00040.safetensors +3 -0
  20. model-00017-of-00040.safetensors +3 -0
  21. model-00018-of-00040.safetensors +3 -0
  22. model-00019-of-00040.safetensors +3 -0
  23. model-00020-of-00040.safetensors +3 -0
  24. model-00021-of-00040.safetensors +3 -0
  25. model-00022-of-00040.safetensors +3 -0
  26. model-00023-of-00040.safetensors +3 -0
  27. model-00024-of-00040.safetensors +3 -0
  28. model-00025-of-00040.safetensors +3 -0
  29. model-00026-of-00040.safetensors +3 -0
  30. model-00027-of-00040.safetensors +3 -0
  31. model-00028-of-00040.safetensors +3 -0
  32. model-00029-of-00040.safetensors +3 -0
  33. model-00030-of-00040.safetensors +3 -0
  34. model-00031-of-00040.safetensors +3 -0
  35. model-00032-of-00040.safetensors +3 -0
  36. model-00033-of-00040.safetensors +3 -0
  37. model-00034-of-00040.safetensors +3 -0
  38. model-00035-of-00040.safetensors +3 -0
  39. model-00036-of-00040.safetensors +3 -0
  40. model-00037-of-00040.safetensors +3 -0
  41. model-00038-of-00040.safetensors +3 -0
  42. model-00039-of-00040.safetensors +3 -0
  43. model-00040-of-00040.safetensors +3 -0
  44. model.safetensors.index.json +3 -0
  45. special_tokens_map.json +16 -0
  46. tokenizer.json +3 -0
  47. tokenizer_config.json +299 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [gMASK]<sop>
2
+ {%- set effective_reasoning_effort = 'high' if reasoning_effort is defined and reasoning_effort == 'high' else 'max' -%}
3
+ {%- if (enable_thinking is not defined or enable_thinking) and effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}
4
+ {%- if tools -%}
5
+ {%- macro tool_to_json(tool) -%}
6
+ {%- set ns_tool = namespace(first=true) -%}
7
+ {{ '{' -}}
8
+ {%- for k, v in tool.items() -%}
9
+ {%- if k != 'defer_loading' and k != 'strict' -%}
10
+ {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
11
+ {%- set ns_tool.first = false -%}
12
+ "{{ k }}": {{ v | tojson(ensure_ascii=False) }}
13
+ {%- endif -%}
14
+ {%- endfor -%}
15
+ {{- '}' -}}
16
+ {%- endmacro -%}
17
+ <|system|>
18
+ # Tools
19
+
20
+ You may call one or more functions to assist with the user query.
21
+
22
+ You are provided with function signatures within <tools></tools> XML tags:
23
+ <tools>
24
+ {% for tool in tools %}
25
+ {%- if 'function' in tool -%}
26
+ {%- set tool = tool['function'] -%}
27
+ {%- endif -%}
28
+ {% if tool.defer_loading is not defined or not tool.defer_loading %}
29
+ {{ tool_to_json(tool) }}
30
+ {% endif %}
31
+ {% endfor %}
32
+ </tools>
33
+
34
+ For each function call, output the function name and arguments within the following XML format:
35
+ <tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
36
+ {%- macro visible_text(content) -%}
37
+ {%- if content is string -%}
38
+ {{- content }}
39
+ {%- elif content is iterable and content is not mapping -%}
40
+ {%- for item in content -%}
41
+ {%- if item is mapping and item.type == 'text' -%}
42
+ {{- item.text }}
43
+ {%- elif item is string -%}
44
+ {{- item }}
45
+ {%- elif item is mapping and item.type in ['image', 'image_url', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%}
46
+ {%- set media_type = item.type | replace('_url', '') | replace('input_', '') -%}
47
+ {{- "<reminder>You are unable to process this " ~ media_type ~ " because you don't have multi-modal input ability. Try different methods.</reminder>" }}
48
+ {%- endif -%}
49
+ {%- endfor -%}
50
+ {%- else -%}
51
+ {{- content }}
52
+ {%- endif -%}
53
+ {%- endmacro -%}
54
+ {%- set ns = namespace(last_user_index=-1) -%}
55
+ {%- for m in messages %}
56
+ {%- if m.role == 'user' %}
57
+ {%- set ns.last_user_index = loop.index0 -%}
58
+ {%- endif %}
59
+ {%- endfor %}
60
+ {%- for m in messages -%}
61
+ {%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
62
+ {%- elif m.role == 'assistant' -%}
63
+ <|assistant|>
64
+ {%- set content = visible_text(m.content) %}
65
+ {%- if m.reasoning_content is string %}
66
+ {%- set reasoning_content = m.reasoning_content %}
67
+ {%- elif '</think>' in content %}
68
+ {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
69
+ {%- set content = content.split('</think>')[-1] %}
70
+ {%- endif %}
71
+ {%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}
72
+ {{ '<think>' + reasoning_content + '</think>'}}
73
+ {%- else -%}
74
+ {{ '<think></think>' }}
75
+ {%- endif -%}
76
+ {%- if content.strip() -%}
77
+ {{ content.strip() }}
78
+ {%- endif -%}
79
+ {% if m.tool_calls %}
80
+ {% for tc in m.tool_calls %}
81
+ {%- if tc.function %}
82
+ {%- set tc = tc.function %}
83
+ {%- endif %}
84
+ {{- '<tool_call>' + tc.name -}}
85
+ {% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
86
+ {% endif %}
87
+ {%- elif m.role == 'tool' -%}
88
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
89
+ {{- '<|observation|>' -}}
90
+ {%- endif %}
91
+ {%- if m.content is string -%}
92
+ {{- '<tool_response>' + m.content + '</tool_response>' -}}
93
+ {%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0.type == "tool_reference" -%}
94
+ {{- '<tool_response><tools>\n' -}}
95
+ {% for tr in m.content %}
96
+ {%- for tool in tools -%}
97
+ {%- if 'function' in tool -%}
98
+ {%- set tool = tool['function'] -%}
99
+ {%- endif -%}
100
+ {%- if tool.name == tr.name -%}
101
+ {{- tool_to_json(tool) + '\n' -}}
102
+ {%- endif -%}
103
+ {%- endfor -%}
104
+ {%- endfor -%}
105
+ {{- '</tools></tool_response>' -}}
106
+ {%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0 is mapping and m.content.0.output is defined -%}
107
+ {%- for tr in m.content -%}
108
+ {{- '<tool_response>' + tr.output + '</tool_response>' -}}
109
+ {%- endfor -%}
110
+ {%- else -%}
111
+ {{- '<tool_response>' + visible_text(m.content) + '</tool_response>' -}}
112
+ {% endif -%}
113
+ {%- elif m.role == 'system' -%}
114
+ <|system|>{{ visible_text(m.content) }}
115
+ {%- endif -%}
116
+ {%- endfor -%}
117
+ {%- if add_generation_prompt -%}
118
+ <|assistant|>{{- '<think></think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
119
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,229 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GlmMoeDsaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": [
10
+ 154820,
11
+ 154827,
12
+ 154829
13
+ ],
14
+ "ep_size": 1,
15
+ "first_k_dense_replace": 3,
16
+ "head_dim": 192,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 6144,
19
+ "index_head_dim": 128,
20
+ "index_n_heads": 32,
21
+ "index_share_for_mtp_iteration": true,
22
+ "index_skip_topk_offset": 3,
23
+ "index_topk": 2048,
24
+ "index_topk_freq": 4,
25
+ "index_topk_pattern": null,
26
+ "indexer_rope_interleave": true,
27
+ "indexer_types": [
28
+ "full",
29
+ "full",
30
+ "full",
31
+ "shared",
32
+ "shared",
33
+ "shared",
34
+ "full",
35
+ "shared",
36
+ "shared",
37
+ "shared",
38
+ "full",
39
+ "shared",
40
+ "shared",
41
+ "shared",
42
+ "full",
43
+ "shared",
44
+ "shared",
45
+ "shared",
46
+ "full",
47
+ "shared",
48
+ "shared",
49
+ "shared",
50
+ "full",
51
+ "shared",
52
+ "shared",
53
+ "shared",
54
+ "full",
55
+ "shared",
56
+ "shared",
57
+ "shared",
58
+ "full",
59
+ "shared",
60
+ "shared",
61
+ "shared",
62
+ "full",
63
+ "shared",
64
+ "shared",
65
+ "shared",
66
+ "full",
67
+ "shared",
68
+ "shared",
69
+ "shared",
70
+ "full",
71
+ "shared",
72
+ "shared",
73
+ "shared",
74
+ "full",
75
+ "shared",
76
+ "shared",
77
+ "shared",
78
+ "full",
79
+ "shared",
80
+ "shared",
81
+ "shared",
82
+ "full",
83
+ "shared",
84
+ "shared",
85
+ "shared",
86
+ "full",
87
+ "shared",
88
+ "shared",
89
+ "shared",
90
+ "full",
91
+ "shared",
92
+ "shared",
93
+ "shared",
94
+ "full",
95
+ "shared",
96
+ "shared",
97
+ "shared",
98
+ "full",
99
+ "shared",
100
+ "shared",
101
+ "shared",
102
+ "full",
103
+ "shared",
104
+ "shared",
105
+ "shared"
106
+ ],
107
+ "initializer_range": 0.02,
108
+ "intermediate_size": 12288,
109
+ "kv_lora_rank": 512,
110
+ "max_position_embeddings": 1048576,
111
+ "mlp_layer_types": [
112
+ "dense",
113
+ "dense",
114
+ "dense",
115
+ "sparse",
116
+ "sparse",
117
+ "sparse",
118
+ "sparse",
119
+ "sparse",
120
+ "sparse",
121
+ "sparse",
122
+ "sparse",
123
+ "sparse",
124
+ "sparse",
125
+ "sparse",
126
+ "sparse",
127
+ "sparse",
128
+ "sparse",
129
+ "sparse",
130
+ "sparse",
131
+ "sparse",
132
+ "sparse",
133
+ "sparse",
134
+ "sparse",
135
+ "sparse",
136
+ "sparse",
137
+ "sparse",
138
+ "sparse",
139
+ "sparse",
140
+ "sparse",
141
+ "sparse",
142
+ "sparse",
143
+ "sparse",
144
+ "sparse",
145
+ "sparse",
146
+ "sparse",
147
+ "sparse",
148
+ "sparse",
149
+ "sparse",
150
+ "sparse",
151
+ "sparse",
152
+ "sparse",
153
+ "sparse",
154
+ "sparse",
155
+ "sparse",
156
+ "sparse",
157
+ "sparse",
158
+ "sparse",
159
+ "sparse",
160
+ "sparse",
161
+ "sparse",
162
+ "sparse",
163
+ "sparse",
164
+ "sparse",
165
+ "sparse",
166
+ "sparse",
167
+ "sparse",
168
+ "sparse",
169
+ "sparse",
170
+ "sparse",
171
+ "sparse",
172
+ "sparse",
173
+ "sparse",
174
+ "sparse",
175
+ "sparse",
176
+ "sparse",
177
+ "sparse",
178
+ "sparse",
179
+ "sparse",
180
+ "sparse",
181
+ "sparse",
182
+ "sparse",
183
+ "sparse",
184
+ "sparse",
185
+ "sparse",
186
+ "sparse",
187
+ "sparse",
188
+ "sparse",
189
+ "sparse"
190
+ ],
191
+ "model_type": "deepseek_v3",
192
+ "moe_intermediate_size": 2048,
193
+ "moe_layer_freq": 1,
194
+ "n_group": 1,
195
+ "n_routed_experts": 256,
196
+ "n_shared_experts": 1,
197
+ "norm_topk_prob": true,
198
+ "num_attention_heads": 64,
199
+ "num_experts_per_tok": 8,
200
+ "num_hidden_layers": 78,
201
+ "num_key_value_heads": 64,
202
+ "num_nextn_predict_layers": 1,
203
+ "pad_token_id": 154820,
204
+ "pretraining_tp": 1,
205
+ "q_lora_rank": 2048,
206
+ "qk_head_dim": 256,
207
+ "qk_nope_head_dim": 192,
208
+ "qk_rope_head_dim": 64,
209
+ "quantization_config": {
210
+ "quant_method": "w4afp8"
211
+ },
212
+ "rms_norm_eps": 1e-05,
213
+ "rope_interleave": true,
214
+ "rope_parameters": {
215
+ "rope_theta": 8000000,
216
+ "rope_type": "default"
217
+ },
218
+ "rope_scaling": null,
219
+ "rope_theta": 10000.0,
220
+ "routed_scaling_factor": 2.5,
221
+ "scoring_func": "sigmoid",
222
+ "tie_word_embeddings": false,
223
+ "topk_group": 1,
224
+ "topk_method": "noaux_tc",
225
+ "transformers_version": "4.57.6",
226
+ "use_cache": false,
227
+ "v_head_dim": 256,
228
+ "vocab_size": 154880
229
+ }
model-00001-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68ab6ace50334cb51a11e79c07f860aa8c02f40abc0492f5d71f4d4269157503
3
+ size 9995981450
model-00002-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d6aeadf3f90604c6bba7a3ae24c28cd1316ad17097b446b14f5ff4417aaec4
3
+ size 9995407970
model-00003-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2deec6de36d6b271b25df19031e40b2521bea2ad19d9c38b2e7bca6501e5129
3
+ size 9995407970
model-00004-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10f7a2ff5b695b3326c8da659986f0114f319724899eb18aa0397deef132f9e9
3
+ size 9995408170
model-00005-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5ed909082a4d6fdf9e49e80c4c52b7bc6cb5c204951a648dade22d75196c4f
3
+ size 9995412522
model-00006-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:013d1a1af019bd8d06cebd619f030ea4cba31a4d806c65eeae70345c09f38c00
3
+ size 9997045154
model-00007-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9549aa8ad023f3c63b62e3e8fe3824246d1b5ceb28dd768d1a3fe1188de55b
3
+ size 9995412386
model-00008-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ebb6ece46e41e23f05ecef163888c998cdd2af4f91554be991a0032e96e8d6
3
+ size 9995412338
model-00009-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8753b246870b411761bc4fd76d90d6864929c036020d7899a6bb48dc3a6a512
3
+ size 9995412322
model-00010-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d45ed482f0b6d37711316b8db4f466e45482a2c3883a3c20b4d1c68cff627e
3
+ size 9995412330
model-00011-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f028a2b644ea9f61489953dee1bc7416466061c95db9e74c893fadb5eca9599f
3
+ size 9995412338
model-00012-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e6d10d6a29b3f2f61a4254cabdaa46a9228b31a3da55d4b5b68e05a5c3e11f
3
+ size 9995412322
model-00013-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b848233aa510d6b65b694db768aa8481d1d943906da76b64634a09ec9469e5
3
+ size 9995412330
model-00014-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60b0bd50d36b4c182c24093b934bef765664cdefbc003a3dffb8b460c64c905
3
+ size 9995412410
model-00015-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216fe87ad1bc1ed00a3e2058d36fb4a3a119ef72712835fb284abe08427e3a16
3
+ size 9995412498
model-00016-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9252982b76dfe38ca9eef8ff660cf61c6f1009193687666f9e18a313f449fc9
3
+ size 9995412442
model-00017-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e8b52b1a98ddf5fa27d9b17300755c805e65ce429bd2b3bff45cc5cea1057d
3
+ size 9995412450
model-00018-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c23fae93bea9305963cd6ffff2031d3ed08080f7eb418a1e6b409a2288a14f40
3
+ size 9995412442
model-00019-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e739c3f72af103b831445af0b101e2054489d731374673f4c41e1b9c85ed1a8
3
+ size 9979193460
model-00020-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6803fede2f2140f2b8874654c35f09e96267de2385b35770c58622109cd4ae2d
3
+ size 10000287268
model-00021-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ba7886080dfe735a53d5e87c4293abb7982ef11118243deaa75a09ba15738c
3
+ size 9995412322
model-00022-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa94f8510f677315b72ab335b95d91dab8a49ef0d75b66989fc18063eeb3c36
3
+ size 9995412330
model-00023-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcf31c9f3ffceede6d02eaef73e70b11aaf4bbd8226bbb828cef2d8b569f8180
3
+ size 9995412338
model-00024-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42fe1d4c1f5d79d51fc28e41321926b27fb039dd78cd4c06f566eccc291ed837
3
+ size 9995412322
model-00025-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e25dbcfbdf2a926ea1cb972deb64f3f2d3f3d39789013e3b3a4b7e2d982870
3
+ size 9995412330
model-00026-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e598c782c925264b80ae6995ae61986e8fcdfe91380b85851c9dfcb2c41b9ec7
3
+ size 9995412338
model-00027-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cc6409c87964e59a0f19fdc8486d3bb7bbd0330a9f24d805c7dd655bee91d44
3
+ size 9995412322
model-00028-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3158b4fb27cd9fe9935e34f0d149b032ec6d3c9c506ef0c120dadd741c72cd80
3
+ size 9995412490
model-00029-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9332eacf5dafb677c6ed2c2a76244c000729c9bf866e5d924cd9443f78aebd87
3
+ size 9995412450
model-00030-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a40fd538332dcd6de34914376f796d8b3053ded28ef6e4c89c7d36472d10b3
3
+ size 9995412442
model-00031-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7824f7ab94200e5ff23cf8bb52fb9269c29fca34462ff4eaf111ef16099211
3
+ size 9995412442
model-00032-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f54a8e8862d0f6fb892a3a9dfe84e35dc6ad9979603221c553a79c9aef2bb5
3
+ size 9995412506
model-00033-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40075861f2ff71262ef0f73c2d60c86dbe8cd33cc7809919cf2e7f49ede3324
3
+ size 9997045186
model-00034-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee27bc00e9dbfdbc5b2c4177fa7d002c048865293948ff6c9bcf66aadedc4d9d
3
+ size 9995412386
model-00035-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29d56f849e313c2f0d4b7eeb9e6b4b1a3a4f0d222f95f0854da2d7631d678ddb
3
+ size 9995412330
model-00036-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:395212938e608603cc4d4b774778a60d35e80abe616bc7fe12ac53c8c45fee5d
3
+ size 9995412338
model-00037-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6700f2300c08752061bf00091afb880a897a235c2e0ed6c3c6da3b459c3c8fb1
3
+ size 9995412322
model-00038-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1674af7762be2d5936e48c3ce95beb8bb08fd308dc9c7a82c0b1d1dee0c52a23
3
+ size 9995412330
model-00039-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9242c9525830ba9dd3a12b648b83940807283551cf175dc7478b29ab11e44a5a
3
+ size 9995412338
model-00040-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35310f74283d68d3c706b537d8268fd29819c2bc9e156ccca4aa338e677b1b05
3
+ size 4561901190
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6117ef911614c9fadf1b6536e42265f60ce1354211196f50821239760ed0f82
3
+ size 16363481
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
3
+ size 20217442
tokenizer_config.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "154820": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "154821": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "154822": {
20
+ "content": "[gMASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "154823": {
28
+ "content": "[sMASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "154824": {
36
+ "content": "<sop>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "154825": {
44
+ "content": "<eop>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "154826": {
52
+ "content": "<|system|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "154827": {
60
+ "content": "<|user|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "154828": {
68
+ "content": "<|assistant|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "154829": {
76
+ "content": "<|observation|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "154830": {
84
+ "content": "<|begin_of_image|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "154831": {
92
+ "content": "<|end_of_image|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "154832": {
100
+ "content": "<|begin_of_video|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "154833": {
108
+ "content": "<|end_of_video|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "154834": {
116
+ "content": "<|begin_of_audio|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "154835": {
124
+ "content": "<|end_of_audio|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "154836": {
132
+ "content": "<|begin_of_transcription|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "154837": {
140
+ "content": "<|end_of_transcription|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "154838": {
148
+ "content": "<|code_prefix|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "154839": {
156
+ "content": "<|code_middle|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "154840": {
164
+ "content": "<|code_suffix|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "154841": {
172
+ "content": "<think>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "154842": {
180
+ "content": "</think>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "154843": {
188
+ "content": "<tool_call>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "154844": {
196
+ "content": "</tool_call>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "154845": {
204
+ "content": "<tool_response>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "154846": {
212
+ "content": "</tool_response>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "154847": {
220
+ "content": "<arg_key>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "154848": {
228
+ "content": "</arg_key>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "154849": {
236
+ "content": "<arg_value>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "154850": {
244
+ "content": "</arg_value>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "154851": {
252
+ "content": "/nothink",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "154852": {
260
+ "content": "<|begin_of_box|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "154853": {
268
+ "content": "<|end_of_box|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "154854": {
276
+ "content": "<|image|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "154855": {
284
+ "content": "<|video|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ }
291
+ },
292
+ "clean_up_tokenization_spaces": false,
293
+ "eos_token": "<|endoftext|>",
294
+ "extra_special_tokens": {},
295
+ "model_max_length": 1048576,
296
+ "pad_token": "<|endoftext|>",
297
+ "padding_side": "left",
298
+ "tokenizer_class": "PreTrainedTokenizerFast"
299
+ }