Hugging Face's logo

RedHatAI
/
Qwen3-235B-A22B-NVFP4

Text Generation
Safetensors
qwen3_moe
fp4
vllm
conversational
8-bit precision
compressed-tensors
Model card Files
xet
Community
Shubhra Pandit commited on
Commit
a58efc5
·
1 Parent(s): 0b5d670

Upload model files

Browse files
Files changed (41) hide show
  1. .gitattributes +4 -0
  2. added_tokens.json +28 -0
  3. chat_template.jinja +89 -0
  4. config.json +554 -0
  5. generation_config.json +13 -0
  6. merges.txt +0 -0
  7. model-00001-of-00029.safetensors +3 -0
  8. model-00002-of-00029.safetensors +3 -0
  9. model-00003-of-00029.safetensors +3 -0
  10. model-00004-of-00029.safetensors +3 -0
  11. model-00005-of-00029.safetensors +3 -0
  12. model-00006-of-00029.safetensors +3 -0
  13. model-00007-of-00029.safetensors +3 -0
  14. model-00008-of-00029.safetensors +3 -0
  15. model-00009-of-00029.safetensors +3 -0
  16. model-00010-of-00029.safetensors +3 -0
  17. model-00011-of-00029.safetensors +3 -0
  18. model-00012-of-00029.safetensors +3 -0
  19. model-00013-of-00029.safetensors +3 -0
  20. model-00014-of-00029.safetensors +3 -0
  21. model-00015-of-00029.safetensors +3 -0
  22. model-00016-of-00029.safetensors +3 -0
  23. model-00017-of-00029.safetensors +3 -0
  24. model-00018-of-00029.safetensors +3 -0
  25. model-00019-of-00029.safetensors +3 -0
  26. model-00020-of-00029.safetensors +3 -0
  27. model-00021-of-00029.safetensors +3 -0
  28. model-00022-of-00029.safetensors +3 -0
  29. model-00023-of-00029.safetensors +3 -0
  30. model-00024-of-00029.safetensors +3 -0
  31. model-00025-of-00029.safetensors +3 -0
  32. model-00026-of-00029.safetensors +3 -0
  33. model-00027-of-00029.safetensors +3 -0
  34. model-00028-of-00029.safetensors +3 -0
  35. model-00029-of-00029.safetensors +3 -0
  36. model.safetensors.index.json +3 -0
  37. recipe.yaml +6 -0
  38. special_tokens_map.json +31 -0
  39. tokenizer.json +3 -0
  40. tokenizer_config.json +239 -0
  41. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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
37
+
38
+ *.index.json filter=lfs diff=lfs merge=lfs -text
39
+ *.index.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 message.content is string 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.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,554 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 151645,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 12288,
16
+ "max_position_embeddings": 40960,
17
+ "max_window_layers": 94,
18
+ "mlp_only_layers": [],
19
+ "model_type": "qwen3_moe",
20
+ "moe_intermediate_size": 1536,
21
+ "norm_topk_prob": true,
22
+ "num_attention_heads": 64,
23
+ "num_experts": 128,
24
+ "num_experts_per_tok": 8,
25
+ "num_hidden_layers": 94,
26
+ "num_key_value_heads": 4,
27
+ "output_router_logits": false,
28
+ "quantization_config": {
29
+ "config_groups": {
30
+ "group_0": {
31
+ "format": "nvfp4-pack-quantized",
32
+ "input_activations": {
33
+ "actorder": null,
34
+ "block_structure": null,
35
+ "dynamic": "local",
36
+ "group_size": 16,
37
+ "num_bits": 4,
38
+ "observer": "minmax",
39
+ "observer_kwargs": {},
40
+ "strategy": "tensor_group",
41
+ "symmetric": true,
42
+ "type": "float"
43
+ },
44
+ "output_activations": null,
45
+ "targets": [
46
+ "Linear"
47
+ ],
48
+ "weights": {
49
+ "actorder": null,
50
+ "block_structure": null,
51
+ "dynamic": false,
52
+ "group_size": 16,
53
+ "num_bits": 4,
54
+ "observer": "minmax",
55
+ "observer_kwargs": {},
56
+ "strategy": "tensor_group",
57
+ "symmetric": true,
58
+ "type": "float"
59
+ }
60
+ }
61
+ },
62
+ "format": "nvfp4-pack-quantized",
63
+ "global_compression_ratio": null,
64
+ "ignore": [
65
+ "model.layers.0.self_attn.q_proj",
66
+ "model.layers.0.self_attn.k_proj",
67
+ "model.layers.0.self_attn.v_proj",
68
+ "model.layers.0.self_attn.o_proj",
69
+ "model.layers.0.mlp.gate",
70
+ "model.layers.1.self_attn.q_proj",
71
+ "model.layers.1.self_attn.k_proj",
72
+ "model.layers.1.self_attn.v_proj",
73
+ "model.layers.1.self_attn.o_proj",
74
+ "model.layers.1.mlp.gate",
75
+ "model.layers.2.self_attn.q_proj",
76
+ "model.layers.2.self_attn.k_proj",
77
+ "model.layers.2.self_attn.v_proj",
78
+ "model.layers.2.self_attn.o_proj",
79
+ "model.layers.2.mlp.gate",
80
+ "model.layers.3.self_attn.q_proj",
81
+ "model.layers.3.self_attn.k_proj",
82
+ "model.layers.3.self_attn.v_proj",
83
+ "model.layers.3.self_attn.o_proj",
84
+ "model.layers.3.mlp.gate",
85
+ "model.layers.4.self_attn.q_proj",
86
+ "model.layers.4.self_attn.k_proj",
87
+ "model.layers.4.self_attn.v_proj",
88
+ "model.layers.4.self_attn.o_proj",
89
+ "model.layers.4.mlp.gate",
90
+ "model.layers.5.self_attn.q_proj",
91
+ "model.layers.5.self_attn.k_proj",
92
+ "model.layers.5.self_attn.v_proj",
93
+ "model.layers.5.self_attn.o_proj",
94
+ "model.layers.5.mlp.gate",
95
+ "model.layers.6.self_attn.q_proj",
96
+ "model.layers.6.self_attn.k_proj",
97
+ "model.layers.6.self_attn.v_proj",
98
+ "model.layers.6.self_attn.o_proj",
99
+ "model.layers.6.mlp.gate",
100
+ "model.layers.7.self_attn.q_proj",
101
+ "model.layers.7.self_attn.k_proj",
102
+ "model.layers.7.self_attn.v_proj",
103
+ "model.layers.7.self_attn.o_proj",
104
+ "model.layers.7.mlp.gate",
105
+ "model.layers.8.self_attn.q_proj",
106
+ "model.layers.8.self_attn.k_proj",
107
+ "model.layers.8.self_attn.v_proj",
108
+ "model.layers.8.self_attn.o_proj",
109
+ "model.layers.8.mlp.gate",
110
+ "model.layers.9.self_attn.q_proj",
111
+ "model.layers.9.self_attn.k_proj",
112
+ "model.layers.9.self_attn.v_proj",
113
+ "model.layers.9.self_attn.o_proj",
114
+ "model.layers.9.mlp.gate",
115
+ "model.layers.10.self_attn.q_proj",
116
+ "model.layers.10.self_attn.k_proj",
117
+ "model.layers.10.self_attn.v_proj",
118
+ "model.layers.10.self_attn.o_proj",
119
+ "model.layers.10.mlp.gate",
120
+ "model.layers.11.self_attn.q_proj",
121
+ "model.layers.11.self_attn.k_proj",
122
+ "model.layers.11.self_attn.v_proj",
123
+ "model.layers.11.self_attn.o_proj",
124
+ "model.layers.11.mlp.gate",
125
+ "model.layers.12.self_attn.q_proj",
126
+ "model.layers.12.self_attn.k_proj",
127
+ "model.layers.12.self_attn.v_proj",
128
+ "model.layers.12.self_attn.o_proj",
129
+ "model.layers.12.mlp.gate",
130
+ "model.layers.13.self_attn.q_proj",
131
+ "model.layers.13.self_attn.k_proj",
132
+ "model.layers.13.self_attn.v_proj",
133
+ "model.layers.13.self_attn.o_proj",
134
+ "model.layers.13.mlp.gate",
135
+ "model.layers.14.self_attn.q_proj",
136
+ "model.layers.14.self_attn.k_proj",
137
+ "model.layers.14.self_attn.v_proj",
138
+ "model.layers.14.self_attn.o_proj",
139
+ "model.layers.14.mlp.gate",
140
+ "model.layers.15.self_attn.q_proj",
141
+ "model.layers.15.self_attn.k_proj",
142
+ "model.layers.15.self_attn.v_proj",
143
+ "model.layers.15.self_attn.o_proj",
144
+ "model.layers.15.mlp.gate",
145
+ "model.layers.16.self_attn.q_proj",
146
+ "model.layers.16.self_attn.k_proj",
147
+ "model.layers.16.self_attn.v_proj",
148
+ "model.layers.16.self_attn.o_proj",
149
+ "model.layers.16.mlp.gate",
150
+ "model.layers.17.self_attn.q_proj",
151
+ "model.layers.17.self_attn.k_proj",
152
+ "model.layers.17.self_attn.v_proj",
153
+ "model.layers.17.self_attn.o_proj",
154
+ "model.layers.17.mlp.gate",
155
+ "model.layers.18.self_attn.q_proj",
156
+ "model.layers.18.self_attn.k_proj",
157
+ "model.layers.18.self_attn.v_proj",
158
+ "model.layers.18.self_attn.o_proj",
159
+ "model.layers.18.mlp.gate",
160
+ "model.layers.19.self_attn.q_proj",
161
+ "model.layers.19.self_attn.k_proj",
162
+ "model.layers.19.self_attn.v_proj",
163
+ "model.layers.19.self_attn.o_proj",
164
+ "model.layers.19.mlp.gate",
165
+ "model.layers.20.self_attn.q_proj",
166
+ "model.layers.20.self_attn.k_proj",
167
+ "model.layers.20.self_attn.v_proj",
168
+ "model.layers.20.self_attn.o_proj",
169
+ "model.layers.20.mlp.gate",
170
+ "model.layers.21.self_attn.q_proj",
171
+ "model.layers.21.self_attn.k_proj",
172
+ "model.layers.21.self_attn.v_proj",
173
+ "model.layers.21.self_attn.o_proj",
174
+ "model.layers.21.mlp.gate",
175
+ "model.layers.22.self_attn.q_proj",
176
+ "model.layers.22.self_attn.k_proj",
177
+ "model.layers.22.self_attn.v_proj",
178
+ "model.layers.22.self_attn.o_proj",
179
+ "model.layers.22.mlp.gate",
180
+ "model.layers.23.self_attn.q_proj",
181
+ "model.layers.23.self_attn.k_proj",
182
+ "model.layers.23.self_attn.v_proj",
183
+ "model.layers.23.self_attn.o_proj",
184
+ "model.layers.23.mlp.gate",
185
+ "model.layers.24.self_attn.q_proj",
186
+ "model.layers.24.self_attn.k_proj",
187
+ "model.layers.24.self_attn.v_proj",
188
+ "model.layers.24.self_attn.o_proj",
189
+ "model.layers.24.mlp.gate",
190
+ "model.layers.25.self_attn.q_proj",
191
+ "model.layers.25.self_attn.k_proj",
192
+ "model.layers.25.self_attn.v_proj",
193
+ "model.layers.25.self_attn.o_proj",
194
+ "model.layers.25.mlp.gate",
195
+ "model.layers.26.self_attn.q_proj",
196
+ "model.layers.26.self_attn.k_proj",
197
+ "model.layers.26.self_attn.v_proj",
198
+ "model.layers.26.self_attn.o_proj",
199
+ "model.layers.26.mlp.gate",
200
+ "model.layers.27.self_attn.q_proj",
201
+ "model.layers.27.self_attn.k_proj",
202
+ "model.layers.27.self_attn.v_proj",
203
+ "model.layers.27.self_attn.o_proj",
204
+ "model.layers.27.mlp.gate",
205
+ "model.layers.28.self_attn.q_proj",
206
+ "model.layers.28.self_attn.k_proj",
207
+ "model.layers.28.self_attn.v_proj",
208
+ "model.layers.28.self_attn.o_proj",
209
+ "model.layers.28.mlp.gate",
210
+ "model.layers.29.self_attn.q_proj",
211
+ "model.layers.29.self_attn.k_proj",
212
+ "model.layers.29.self_attn.v_proj",
213
+ "model.layers.29.self_attn.o_proj",
214
+ "model.layers.29.mlp.gate",
215
+ "model.layers.30.self_attn.q_proj",
216
+ "model.layers.30.self_attn.k_proj",
217
+ "model.layers.30.self_attn.v_proj",
218
+ "model.layers.30.self_attn.o_proj",
219
+ "model.layers.30.mlp.gate",
220
+ "model.layers.31.self_attn.q_proj",
221
+ "model.layers.31.self_attn.k_proj",
222
+ "model.layers.31.self_attn.v_proj",
223
+ "model.layers.31.self_attn.o_proj",
224
+ "model.layers.31.mlp.gate",
225
+ "model.layers.32.self_attn.q_proj",
226
+ "model.layers.32.self_attn.k_proj",
227
+ "model.layers.32.self_attn.v_proj",
228
+ "model.layers.32.self_attn.o_proj",
229
+ "model.layers.32.mlp.gate",
230
+ "model.layers.33.self_attn.q_proj",
231
+ "model.layers.33.self_attn.k_proj",
232
+ "model.layers.33.self_attn.v_proj",
233
+ "model.layers.33.self_attn.o_proj",
234
+ "model.layers.33.mlp.gate",
235
+ "model.layers.34.self_attn.q_proj",
236
+ "model.layers.34.self_attn.k_proj",
237
+ "model.layers.34.self_attn.v_proj",
238
+ "model.layers.34.self_attn.o_proj",
239
+ "model.layers.34.mlp.gate",
240
+ "model.layers.35.self_attn.q_proj",
241
+ "model.layers.35.self_attn.k_proj",
242
+ "model.layers.35.self_attn.v_proj",
243
+ "model.layers.35.self_attn.o_proj",
244
+ "model.layers.35.mlp.gate",
245
+ "model.layers.36.self_attn.q_proj",
246
+ "model.layers.36.self_attn.k_proj",
247
+ "model.layers.36.self_attn.v_proj",
248
+ "model.layers.36.self_attn.o_proj",
249
+ "model.layers.36.mlp.gate",
250
+ "model.layers.37.self_attn.q_proj",
251
+ "model.layers.37.self_attn.k_proj",
252
+ "model.layers.37.self_attn.v_proj",
253
+ "model.layers.37.self_attn.o_proj",
254
+ "model.layers.37.mlp.gate",
255
+ "model.layers.38.self_attn.q_proj",
256
+ "model.layers.38.self_attn.k_proj",
257
+ "model.layers.38.self_attn.v_proj",
258
+ "model.layers.38.self_attn.o_proj",
259
+ "model.layers.38.mlp.gate",
260
+ "model.layers.39.self_attn.q_proj",
261
+ "model.layers.39.self_attn.k_proj",
262
+ "model.layers.39.self_attn.v_proj",
263
+ "model.layers.39.self_attn.o_proj",
264
+ "model.layers.39.mlp.gate",
265
+ "model.layers.40.self_attn.q_proj",
266
+ "model.layers.40.self_attn.k_proj",
267
+ "model.layers.40.self_attn.v_proj",
268
+ "model.layers.40.self_attn.o_proj",
269
+ "model.layers.40.mlp.gate",
270
+ "model.layers.41.self_attn.q_proj",
271
+ "model.layers.41.self_attn.k_proj",
272
+ "model.layers.41.self_attn.v_proj",
273
+ "model.layers.41.self_attn.o_proj",
274
+ "model.layers.41.mlp.gate",
275
+ "model.layers.42.self_attn.q_proj",
276
+ "model.layers.42.self_attn.k_proj",
277
+ "model.layers.42.self_attn.v_proj",
278
+ "model.layers.42.self_attn.o_proj",
279
+ "model.layers.42.mlp.gate",
280
+ "model.layers.43.self_attn.q_proj",
281
+ "model.layers.43.self_attn.k_proj",
282
+ "model.layers.43.self_attn.v_proj",
283
+ "model.layers.43.self_attn.o_proj",
284
+ "model.layers.43.mlp.gate",
285
+ "model.layers.44.self_attn.q_proj",
286
+ "model.layers.44.self_attn.k_proj",
287
+ "model.layers.44.self_attn.v_proj",
288
+ "model.layers.44.self_attn.o_proj",
289
+ "model.layers.44.mlp.gate",
290
+ "model.layers.45.self_attn.q_proj",
291
+ "model.layers.45.self_attn.k_proj",
292
+ "model.layers.45.self_attn.v_proj",
293
+ "model.layers.45.self_attn.o_proj",
294
+ "model.layers.45.mlp.gate",
295
+ "model.layers.46.self_attn.q_proj",
296
+ "model.layers.46.self_attn.k_proj",
297
+ "model.layers.46.self_attn.v_proj",
298
+ "model.layers.46.self_attn.o_proj",
299
+ "model.layers.46.mlp.gate",
300
+ "model.layers.47.self_attn.q_proj",
301
+ "model.layers.47.self_attn.k_proj",
302
+ "model.layers.47.self_attn.v_proj",
303
+ "model.layers.47.self_attn.o_proj",
304
+ "model.layers.47.mlp.gate",
305
+ "model.layers.48.self_attn.q_proj",
306
+ "model.layers.48.self_attn.k_proj",
307
+ "model.layers.48.self_attn.v_proj",
308
+ "model.layers.48.self_attn.o_proj",
309
+ "model.layers.48.mlp.gate",
310
+ "model.layers.49.self_attn.q_proj",
311
+ "model.layers.49.self_attn.k_proj",
312
+ "model.layers.49.self_attn.v_proj",
313
+ "model.layers.49.self_attn.o_proj",
314
+ "model.layers.49.mlp.gate",
315
+ "model.layers.50.self_attn.q_proj",
316
+ "model.layers.50.self_attn.k_proj",
317
+ "model.layers.50.self_attn.v_proj",
318
+ "model.layers.50.self_attn.o_proj",
319
+ "model.layers.50.mlp.gate",
320
+ "model.layers.51.self_attn.q_proj",
321
+ "model.layers.51.self_attn.k_proj",
322
+ "model.layers.51.self_attn.v_proj",
323
+ "model.layers.51.self_attn.o_proj",
324
+ "model.layers.51.mlp.gate",
325
+ "model.layers.52.self_attn.q_proj",
326
+ "model.layers.52.self_attn.k_proj",
327
+ "model.layers.52.self_attn.v_proj",
328
+ "model.layers.52.self_attn.o_proj",
329
+ "model.layers.52.mlp.gate",
330
+ "model.layers.53.self_attn.q_proj",
331
+ "model.layers.53.self_attn.k_proj",
332
+ "model.layers.53.self_attn.v_proj",
333
+ "model.layers.53.self_attn.o_proj",
334
+ "model.layers.53.mlp.gate",
335
+ "model.layers.54.self_attn.q_proj",
336
+ "model.layers.54.self_attn.k_proj",
337
+ "model.layers.54.self_attn.v_proj",
338
+ "model.layers.54.self_attn.o_proj",
339
+ "model.layers.54.mlp.gate",
340
+ "model.layers.55.self_attn.q_proj",
341
+ "model.layers.55.self_attn.k_proj",
342
+ "model.layers.55.self_attn.v_proj",
343
+ "model.layers.55.self_attn.o_proj",
344
+ "model.layers.55.mlp.gate",
345
+ "model.layers.56.self_attn.q_proj",
346
+ "model.layers.56.self_attn.k_proj",
347
+ "model.layers.56.self_attn.v_proj",
348
+ "model.layers.56.self_attn.o_proj",
349
+ "model.layers.56.mlp.gate",
350
+ "model.layers.57.self_attn.q_proj",
351
+ "model.layers.57.self_attn.k_proj",
352
+ "model.layers.57.self_attn.v_proj",
353
+ "model.layers.57.self_attn.o_proj",
354
+ "model.layers.57.mlp.gate",
355
+ "model.layers.58.self_attn.q_proj",
356
+ "model.layers.58.self_attn.k_proj",
357
+ "model.layers.58.self_attn.v_proj",
358
+ "model.layers.58.self_attn.o_proj",
359
+ "model.layers.58.mlp.gate",
360
+ "model.layers.59.self_attn.q_proj",
361
+ "model.layers.59.self_attn.k_proj",
362
+ "model.layers.59.self_attn.v_proj",
363
+ "model.layers.59.self_attn.o_proj",
364
+ "model.layers.59.mlp.gate",
365
+ "model.layers.60.self_attn.q_proj",
366
+ "model.layers.60.self_attn.k_proj",
367
+ "model.layers.60.self_attn.v_proj",
368
+ "model.layers.60.self_attn.o_proj",
369
+ "model.layers.60.mlp.gate",
370
+ "model.layers.61.self_attn.q_proj",
371
+ "model.layers.61.self_attn.k_proj",
372
+ "model.layers.61.self_attn.v_proj",
373
+ "model.layers.61.self_attn.o_proj",
374
+ "model.layers.61.mlp.gate",
375
+ "model.layers.62.self_attn.q_proj",
376
+ "model.layers.62.self_attn.k_proj",
377
+ "model.layers.62.self_attn.v_proj",
378
+ "model.layers.62.self_attn.o_proj",
379
+ "model.layers.62.mlp.gate",
380
+ "model.layers.63.self_attn.q_proj",
381
+ "model.layers.63.self_attn.k_proj",
382
+ "model.layers.63.self_attn.v_proj",
383
+ "model.layers.63.self_attn.o_proj",
384
+ "model.layers.63.mlp.gate",
385
+ "model.layers.64.self_attn.q_proj",
386
+ "model.layers.64.self_attn.k_proj",
387
+ "model.layers.64.self_attn.v_proj",
388
+ "model.layers.64.self_attn.o_proj",
389
+ "model.layers.64.mlp.gate",
390
+ "model.layers.65.self_attn.q_proj",
391
+ "model.layers.65.self_attn.k_proj",
392
+ "model.layers.65.self_attn.v_proj",
393
+ "model.layers.65.self_attn.o_proj",
394
+ "model.layers.65.mlp.gate",
395
+ "model.layers.66.self_attn.q_proj",
396
+ "model.layers.66.self_attn.k_proj",
397
+ "model.layers.66.self_attn.v_proj",
398
+ "model.layers.66.self_attn.o_proj",
399
+ "model.layers.66.mlp.gate",
400
+ "model.layers.67.self_attn.q_proj",
401
+ "model.layers.67.self_attn.k_proj",
402
+ "model.layers.67.self_attn.v_proj",
403
+ "model.layers.67.self_attn.o_proj",
404
+ "model.layers.67.mlp.gate",
405
+ "model.layers.68.self_attn.q_proj",
406
+ "model.layers.68.self_attn.k_proj",
407
+ "model.layers.68.self_attn.v_proj",
408
+ "model.layers.68.self_attn.o_proj",
409
+ "model.layers.68.mlp.gate",
410
+ "model.layers.69.self_attn.q_proj",
411
+ "model.layers.69.self_attn.k_proj",
412
+ "model.layers.69.self_attn.v_proj",
413
+ "model.layers.69.self_attn.o_proj",
414
+ "model.layers.69.mlp.gate",
415
+ "model.layers.70.self_attn.q_proj",
416
+ "model.layers.70.self_attn.k_proj",
417
+ "model.layers.70.self_attn.v_proj",
418
+ "model.layers.70.self_attn.o_proj",
419
+ "model.layers.70.mlp.gate",
420
+ "model.layers.71.self_attn.q_proj",
421
+ "model.layers.71.self_attn.k_proj",
422
+ "model.layers.71.self_attn.v_proj",
423
+ "model.layers.71.self_attn.o_proj",
424
+ "model.layers.71.mlp.gate",
425
+ "model.layers.72.self_attn.q_proj",
426
+ "model.layers.72.self_attn.k_proj",
427
+ "model.layers.72.self_attn.v_proj",
428
+ "model.layers.72.self_attn.o_proj",
429
+ "model.layers.72.mlp.gate",
430
+ "model.layers.73.self_attn.q_proj",
431
+ "model.layers.73.self_attn.k_proj",
432
+ "model.layers.73.self_attn.v_proj",
433
+ "model.layers.73.self_attn.o_proj",
434
+ "model.layers.73.mlp.gate",
435
+ "model.layers.74.self_attn.q_proj",
436
+ "model.layers.74.self_attn.k_proj",
437
+ "model.layers.74.self_attn.v_proj",
438
+ "model.layers.74.self_attn.o_proj",
439
+ "model.layers.74.mlp.gate",
440
+ "model.layers.75.self_attn.q_proj",
441
+ "model.layers.75.self_attn.k_proj",
442
+ "model.layers.75.self_attn.v_proj",
443
+ "model.layers.75.self_attn.o_proj",
444
+ "model.layers.75.mlp.gate",
445
+ "model.layers.76.self_attn.q_proj",
446
+ "model.layers.76.self_attn.k_proj",
447
+ "model.layers.76.self_attn.v_proj",
448
+ "model.layers.76.self_attn.o_proj",
449
+ "model.layers.76.mlp.gate",
450
+ "model.layers.77.self_attn.q_proj",
451
+ "model.layers.77.self_attn.k_proj",
452
+ "model.layers.77.self_attn.v_proj",
453
+ "model.layers.77.self_attn.o_proj",
454
+ "model.layers.77.mlp.gate",
455
+ "model.layers.78.self_attn.q_proj",
456
+ "model.layers.78.self_attn.k_proj",
457
+ "model.layers.78.self_attn.v_proj",
458
+ "model.layers.78.self_attn.o_proj",
459
+ "model.layers.78.mlp.gate",
460
+ "model.layers.79.self_attn.q_proj",
461
+ "model.layers.79.self_attn.k_proj",
462
+ "model.layers.79.self_attn.v_proj",
463
+ "model.layers.79.self_attn.o_proj",
464
+ "model.layers.79.mlp.gate",
465
+ "model.layers.80.self_attn.q_proj",
466
+ "model.layers.80.self_attn.k_proj",
467
+ "model.layers.80.self_attn.v_proj",
468
+ "model.layers.80.self_attn.o_proj",
469
+ "model.layers.80.mlp.gate",
470
+ "model.layers.81.self_attn.q_proj",
471
+ "model.layers.81.self_attn.k_proj",
472
+ "model.layers.81.self_attn.v_proj",
473
+ "model.layers.81.self_attn.o_proj",
474
+ "model.layers.81.mlp.gate",
475
+ "model.layers.82.self_attn.q_proj",
476
+ "model.layers.82.self_attn.k_proj",
477
+ "model.layers.82.self_attn.v_proj",
478
+ "model.layers.82.self_attn.o_proj",
479
+ "model.layers.82.mlp.gate",
480
+ "model.layers.83.self_attn.q_proj",
481
+ "model.layers.83.self_attn.k_proj",
482
+ "model.layers.83.self_attn.v_proj",
483
+ "model.layers.83.self_attn.o_proj",
484
+ "model.layers.83.mlp.gate",
485
+ "model.layers.84.self_attn.q_proj",
486
+ "model.layers.84.self_attn.k_proj",
487
+ "model.layers.84.self_attn.v_proj",
488
+ "model.layers.84.self_attn.o_proj",
489
+ "model.layers.84.mlp.gate",
490
+ "model.layers.85.self_attn.q_proj",
491
+ "model.layers.85.self_attn.k_proj",
492
+ "model.layers.85.self_attn.v_proj",
493
+ "model.layers.85.self_attn.o_proj",
494
+ "model.layers.85.mlp.gate",
495
+ "model.layers.86.self_attn.q_proj",
496
+ "model.layers.86.self_attn.k_proj",
497
+ "model.layers.86.self_attn.v_proj",
498
+ "model.layers.86.self_attn.o_proj",
499
+ "model.layers.86.mlp.gate",
500
+ "model.layers.87.self_attn.q_proj",
501
+ "model.layers.87.self_attn.k_proj",
502
+ "model.layers.87.self_attn.v_proj",
503
+ "model.layers.87.self_attn.o_proj",
504
+ "model.layers.87.mlp.gate",
505
+ "model.layers.88.self_attn.q_proj",
506
+ "model.layers.88.self_attn.k_proj",
507
+ "model.layers.88.self_attn.v_proj",
508
+ "model.layers.88.self_attn.o_proj",
509
+ "model.layers.88.mlp.gate",
510
+ "model.layers.89.self_attn.q_proj",
511
+ "model.layers.89.self_attn.k_proj",
512
+ "model.layers.89.self_attn.v_proj",
513
+ "model.layers.89.self_attn.o_proj",
514
+ "model.layers.89.mlp.gate",
515
+ "model.layers.90.self_attn.q_proj",
516
+ "model.layers.90.self_attn.k_proj",
517
+ "model.layers.90.self_attn.v_proj",
518
+ "model.layers.90.self_attn.o_proj",
519
+ "model.layers.90.mlp.gate",
520
+ "model.layers.91.self_attn.q_proj",
521
+ "model.layers.91.self_attn.k_proj",
522
+ "model.layers.91.self_attn.v_proj",
523
+ "model.layers.91.self_attn.o_proj",
524
+ "model.layers.91.mlp.gate",
525
+ "model.layers.92.self_attn.q_proj",
526
+ "model.layers.92.self_attn.k_proj",
527
+ "model.layers.92.self_attn.v_proj",
528
+ "model.layers.92.self_attn.o_proj",
529
+ "model.layers.92.mlp.gate",
530
+ "model.layers.93.self_attn.q_proj",
531
+ "model.layers.93.self_attn.k_proj",
532
+ "model.layers.93.self_attn.v_proj",
533
+ "model.layers.93.self_attn.o_proj",
534
+ "model.layers.93.mlp.gate",
535
+ "lm_head"
536
+ ],
537
+ "kv_cache_scheme": null,
538
+ "quant_method": "compressed-tensors",
539
+ "quantization_status": "compressed",
540
+ "sparsity_config": {},
541
+ "transform_config": {},
542
+ "version": "0.12.3.a20251013"
543
+ },
544
+ "rms_norm_eps": 1e-06,
545
+ "rope_scaling": null,
546
+ "rope_theta": 1000000.0,
547
+ "router_aux_loss_coef": 0.001,
548
+ "sliding_window": null,
549
+ "tie_word_embeddings": false,
550
+ "transformers_version": "4.57.0.dev0",
551
+ "use_cache": true,
552
+ "use_sliding_window": false,
553
+ "vocab_size": 151936
554
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.0.dev0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef3534d3e3961a6599e288c328e78f489844c62e7ed92e40e6dd4026dee4baf
3
+ size 4999200048
model-00002-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ae6b1931242f3f287b39b711836d5d430e582cecb2633ef63d68278b788460
3
+ size 5000439192
model-00003-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a4e35f43f2ed23dd2d3570a7597f1e37159bc3ac550c9bfc78bfe43dec8c9a
3
+ size 4998995224
model-00004-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09406e931a8a0e57f8fa3f8c5a774be98981ce67d40d1f15b354818749d5b10e
3
+ size 5000442896
model-00005-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749b2a1f04008dbadeeb2d603ef2d1ab63af3fddd4b2c419db508f90d85fd7cf
3
+ size 5000444344
model-00006-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6afd1f9d3b74de7f5fe4ec62cee3325945620d6511bb16b1f27d82430fc014ce
3
+ size 4999000336
model-00007-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f83e63eb84ef456c8d03e12982b48d14d6bbcf2af21bc0e0273b3ff8537d84
3
+ size 5000444280
model-00008-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f0be6da7bc93e928b5fdde49c4c860890f25f394e58eaf07add715b6271501
3
+ size 5000444344
model-00009-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1827be8e8498ae4221c4f4949d5d4ea9f9f2178b6bb199fc710bb45b3583d50d
3
+ size 4999000368
model-00010-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81a1e527faffb0ee6b8a5529a62a6de6ff52f5bbb3f59709ef5f26dadcfc3bd
3
+ size 5000444256
model-00011-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f5275fde5c373e5b4b959a0202ec6d5cc16df159d8303454c1d3c551bd774fe
3
+ size 5000444344
model-00012-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec315eca06dedcde3458e02e36af8fc81f1e018cc253f1b07c846a275dc0556b
3
+ size 4999000400
model-00013-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8549cdeaec577d5a4b89b3de32540898a7efb3b3b1b4aa93eba11926ed6b626e
3
+ size 5000444224
model-00014-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4e3e7f5470b75694a2133135d270827bbb8dea97881bfade3f4dc2da8cd69a
3
+ size 5000444336
model-00015-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bc500bad9d519ea46b7387bf029f889b3bc1eca689d621f7e1afbd42513bc3b
3
+ size 4959157280
model-00016-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c447e460c42e1b497c91289aaadf0ac07c1d3ee0b72db692ff2f94b68b241b2
3
+ size 4997813648
model-00017-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b5b904ad400c7a51bf491db022bfaafd9e6b553e4a7bfabbffc35986497cb00
3
+ size 5000444344
model-00018-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07f581fa716908e9b01a6fbbbd7b5e16106b374a1a6e773cadb7873e7dbbc67
3
+ size 4954448424
model-00019-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cfc96c2932360b8e1d3f4267dd077a55576edcdc04a27e332725252ee482c12
3
+ size 4998983344
model-00020-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04c7feabe20f6ca39009b37af7be4853b041963f292d36cf37a34bddc3b69be4
3
+ size 5000444344
model-00021-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e315a5d77752dfef7f4950ff2216c7aba5ff8a53f301f25ca967b089d85e351f
3
+ size 5000444648
model-00022-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5628f7231f0a67b4ab45940b2c9e1db12292d26abf0d17946005cec8f6306111
3
+ size 4998999976
model-00023-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4cb924a68b8f2165ad281de21465cc72a0862112b048d1b549011112306c598
3
+ size 5000444344
model-00024-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c3e8cf02a9cbf1578dd85621926bf09d04ce1adc5105d8e9e9acf4f20320a33
3
+ size 5000444608
model-00025-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b86a9eb6ffc52dd1fda5ade370a738b121b89adc23e271f8b29688ab8c5208b
3
+ size 4999000016
model-00026-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3038fb1270703d72ceb99dfdbd100a9f800417a6314b143ae1178acf293dbcf7
3
+ size 5000444336
model-00027-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b11faac374b72c6616087236463ea2bfe821d087fd31935a78b37a9eee882285
3
+ size 5000444584
model-00028-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c6953eee5c85bb8cda813b40199f7460bd0fb042948292aa12a134fbebb89ef
3
+ size 4999000040
model-00029-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81d179ec92b1cb848c6f7c9e3ae02f54a632c6387930b335f3a13bb0cb2e443f
3
+ size 3844734960
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e352551d65cf3021a8529b777425f35323be4d8bee29faaace919c6fb729f10f
3
+ size 14489617
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: ['re:.*lm_head.*', 're:.*mlp.gate$', 're:.*self_attn']
6
+ scheme: NVFP4
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff