Hugging Face's logo

lukealonso
/
GLM-5-NVFP4

Safetensors
glm_moe_dsa
8-bit precision
modelopt
Model card Files
xet
Community
2
lukealonso commited on
Commit
585d568
·
verified ·
1 Parent(s): dfbd9b2

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +86 -0
  3. config.json +268 -0
  4. generation_config.json +74 -0
  5. hf_quant_config.json +113 -0
  6. model-00006-of-00082.safetensors +3 -0
  7. model-00008-of-00082.safetensors +3 -0
  8. model-00011-of-00082.safetensors +3 -0
  9. model-00014-of-00082.safetensors +3 -0
  10. model-00016-of-00082.safetensors +3 -0
  11. model-00019-of-00082.safetensors +3 -0
  12. model-00021-of-00082.safetensors +3 -0
  13. model-00022-of-00082.safetensors +3 -0
  14. model-00023-of-00082.safetensors +3 -0
  15. model-00025-of-00082.safetensors +3 -0
  16. model-00026-of-00082.safetensors +3 -0
  17. model-00027-of-00082.safetensors +3 -0
  18. model-00030-of-00082.safetensors +3 -0
  19. model-00031-of-00082.safetensors +3 -0
  20. model-00034-of-00082.safetensors +3 -0
  21. model-00035-of-00082.safetensors +3 -0
  22. model-00036-of-00082.safetensors +3 -0
  23. model-00037-of-00082.safetensors +3 -0
  24. model-00038-of-00082.safetensors +3 -0
  25. model-00039-of-00082.safetensors +3 -0
  26. model-00042-of-00082.safetensors +3 -0
  27. model-00044-of-00082.safetensors +3 -0
  28. model-00046-of-00082.safetensors +3 -0
  29. model-00048-of-00082.safetensors +3 -0
  30. model-00049-of-00082.safetensors +3 -0
  31. model-00050-of-00082.safetensors +3 -0
  32. model-00051-of-00082.safetensors +3 -0
  33. model-00052-of-00082.safetensors +3 -0
  34. model-00053-of-00082.safetensors +3 -0
  35. model-00054-of-00082.safetensors +3 -0
  36. model-00056-of-00082.safetensors +3 -0
  37. model-00057-of-00082.safetensors +3 -0
  38. model-00058-of-00082.safetensors +3 -0
  39. model-00059-of-00082.safetensors +3 -0
  40. model-00060-of-00082.safetensors +3 -0
  41. model-00062-of-00082.safetensors +3 -0
  42. model-00064-of-00082.safetensors +3 -0
  43. model-00065-of-00082.safetensors +3 -0
  44. model-00066-of-00082.safetensors +3 -0
  45. model-00070-of-00082.safetensors +3 -0
  46. model-00071-of-00082.safetensors +3 -0
  47. model-00073-of-00082.safetensors +3 -0
  48. model-00076-of-00082.safetensors +3 -0
  49. model-00078-of-00082.safetensors +3 -0
  50. tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [gMASK]<sop>
2
+ {%- if tools -%}
3
+ <|system|>
4
+ # Tools
5
+
6
+ You may call one or more functions to assist with the user query.
7
+
8
+ You are provided with function signatures within <tools></tools> XML tags:
9
+ <tools>
10
+ {% for tool in tools %}
11
+ {{ tool | tojson(ensure_ascii=False) }}
12
+ {% endfor %}
13
+ </tools>
14
+
15
+ For each function call, output the function name and arguments within the following XML format:
16
+ <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 -%}
17
+ {%- macro visible_text(content) -%}
18
+ {%- if content is string -%}
19
+ {{- content }}
20
+ {%- elif content is iterable and content is not mapping -%}
21
+ {%- for item in content -%}
22
+ {%- if item is mapping and item.type == 'text' -%}
23
+ {{- item.text }}
24
+ {%- elif item is string -%}
25
+ {{- item }}
26
+ {%- endif -%}
27
+ {%- endfor -%}
28
+ {%- else -%}
29
+ {{- content }}
30
+ {%- endif -%}
31
+ {%- endmacro -%}
32
+ {%- set ns = namespace(last_user_index=-1) %}
33
+ {%- for m in messages %}
34
+ {%- if m.role == 'user' %}
35
+ {% set ns.last_user_index = loop.index0 -%}
36
+ {%- endif %}
37
+ {%- endfor %}
38
+ {% for m in messages %}
39
+ {%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
40
+ {%- elif m.role == 'assistant' -%}
41
+ <|assistant|>
42
+ {%- set reasoning_content = '' %}
43
+ {%- set content = visible_text(m.content) %}
44
+ {%- if m.reasoning_content is string %}
45
+ {%- set reasoning_content = m.reasoning_content %}
46
+ {%- else %}
47
+ {%- if '</think>' in content %}
48
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
49
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
50
+ {%- endif %}
51
+ {%- endif %}
52
+ {%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}
53
+ {{ '<think>' + reasoning_content.strip() + '</think>'}}
54
+ {%- else -%}
55
+ {{ '</think>' }}
56
+ {%- endif -%}
57
+ {%- if content.strip() -%}
58
+ {{ content.strip() }}
59
+ {%- endif -%}
60
+ {% if m.tool_calls %}
61
+ {% for tc in m.tool_calls %}
62
+ {%- if tc.function %}
63
+ {%- set tc = tc.function %}
64
+ {%- endif %}
65
+ {{- '<tool_call>' + tc.name -}}
66
+ {% 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 %}
67
+ {% endif %}
68
+ {%- elif m.role == 'tool' -%}
69
+ {%- if m.content is string -%}
70
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
71
+ {{- '<|observation|>' }}
72
+ {%- endif %}
73
+ {{- '<tool_response>' }}
74
+ {{- m.content }}
75
+ {{- '</tool_response>' }}
76
+ {%- else -%}
77
+ <|observation|>{% for tr in m.content %}
78
+ <tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}
79
+ {% endif -%}
80
+ {%- elif m.role == 'system' -%}
81
+ <|system|>{{ visible_text(m.content) }}
82
+ {%- endif -%}
83
+ {%- endfor -%}
84
+ {%- if add_generation_prompt -%}
85
+ <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
86
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 154880,
3
+ "max_position_embeddings": 202752,
4
+ "hidden_size": 6144,
5
+ "intermediate_size": 12288,
6
+ "num_hidden_layers": 78,
7
+ "mlp_layer_types": [
8
+ "dense",
9
+ "dense",
10
+ "dense",
11
+ "sparse",
12
+ "sparse",
13
+ "sparse",
14
+ "sparse",
15
+ "sparse",
16
+ "sparse",
17
+ "sparse",
18
+ "sparse",
19
+ "sparse",
20
+ "sparse",
21
+ "sparse",
22
+ "sparse",
23
+ "sparse",
24
+ "sparse",
25
+ "sparse",
26
+ "sparse",
27
+ "sparse",
28
+ "sparse",
29
+ "sparse",
30
+ "sparse",
31
+ "sparse",
32
+ "sparse",
33
+ "sparse",
34
+ "sparse",
35
+ "sparse",
36
+ "sparse",
37
+ "sparse",
38
+ "sparse",
39
+ "sparse",
40
+ "sparse",
41
+ "sparse",
42
+ "sparse",
43
+ "sparse",
44
+ "sparse",
45
+ "sparse",
46
+ "sparse",
47
+ "sparse",
48
+ "sparse",
49
+ "sparse",
50
+ "sparse",
51
+ "sparse",
52
+ "sparse",
53
+ "sparse",
54
+ "sparse",
55
+ "sparse",
56
+ "sparse",
57
+ "sparse",
58
+ "sparse",
59
+ "sparse",
60
+ "sparse",
61
+ "sparse",
62
+ "sparse",
63
+ "sparse",
64
+ "sparse",
65
+ "sparse",
66
+ "sparse",
67
+ "sparse",
68
+ "sparse",
69
+ "sparse",
70
+ "sparse",
71
+ "sparse",
72
+ "sparse",
73
+ "sparse",
74
+ "sparse",
75
+ "sparse",
76
+ "sparse",
77
+ "sparse",
78
+ "sparse",
79
+ "sparse",
80
+ "sparse",
81
+ "sparse",
82
+ "sparse",
83
+ "sparse",
84
+ "sparse",
85
+ "sparse"
86
+ ],
87
+ "moe_intermediate_size": 2048,
88
+ "num_attention_heads": 64,
89
+ "n_shared_experts": 1,
90
+ "n_routed_experts": 256,
91
+ "routed_scaling_factor": 2.5,
92
+ "kv_lora_rank": 512,
93
+ "q_lora_rank": 2048,
94
+ "qk_rope_head_dim": 64,
95
+ "v_head_dim": 256,
96
+ "qk_nope_head_dim": 192,
97
+ "qk_head_dim": 256,
98
+ "head_dim": 64,
99
+ "n_group": 1,
100
+ "topk_group": 1,
101
+ "num_experts_per_tok": 8,
102
+ "norm_topk_prob": true,
103
+ "rope_interleave": true,
104
+ "num_key_value_heads": 64,
105
+ "hidden_act": "silu",
106
+ "initializer_range": 0.02,
107
+ "index_topk": 2048,
108
+ "rms_norm_eps": 1e-05,
109
+ "use_cache": true,
110
+ "attention_bias": false,
111
+ "attention_dropout": 0.0,
112
+ "rope_parameters": {
113
+ "rope_theta": 1000000,
114
+ "rope_type": "default"
115
+ },
116
+ "pad_token_id": 154820,
117
+ "bos_token_id": 0,
118
+ "eos_token_id": [
119
+ 154820,
120
+ 154827,
121
+ 154829
122
+ ],
123
+ "tie_word_embeddings": false,
124
+ "return_dict": true,
125
+ "output_hidden_states": false,
126
+ "dtype": "bfloat16",
127
+ "chunk_size_feed_forward": 0,
128
+ "is_encoder_decoder": false,
129
+ "architectures": [
130
+ "GlmMoeDsaForCausalLM"
131
+ ],
132
+ "id2label": {
133
+ "0": "LABEL_0",
134
+ "1": "LABEL_1"
135
+ },
136
+ "label2id": {
137
+ "LABEL_0": 0,
138
+ "LABEL_1": 1
139
+ },
140
+ "problem_type": null,
141
+ "_name_or_path": "zai-org/GLM-5",
142
+ "transformers_version": "5.2.0.dev0",
143
+ "ep_size": 1,
144
+ "first_k_dense_replace": 3,
145
+ "index_head_dim": 128,
146
+ "index_n_heads": 32,
147
+ "indexer_rope_interleave": true,
148
+ "moe_layer_freq": 1,
149
+ "model_type": "glm_moe_dsa",
150
+ "num_nextn_predict_layers": 1,
151
+ "pretraining_tp": 1,
152
+ "scoring_func": "sigmoid",
153
+ "topk_method": "noaux_tc",
154
+ "output_attentions": false,
155
+ "quantization_config": {
156
+ "config_groups": {
157
+ "group_0": {
158
+ "input_activations": {
159
+ "dynamic": false,
160
+ "num_bits": 4,
161
+ "type": "float",
162
+ "group_size": 16
163
+ },
164
+ "weights": {
165
+ "dynamic": false,
166
+ "num_bits": 4,
167
+ "type": "float",
168
+ "group_size": 16
169
+ },
170
+ "targets": [
171
+ "Linear"
172
+ ]
173
+ }
174
+ },
175
+ "ignore": [
176
+ "lm_head",
177
+ "model.layers.0.self_attn*",
178
+ "model.layers.1.self_attn*",
179
+ "model.layers.10.self_attn*",
180
+ "model.layers.11.self_attn*",
181
+ "model.layers.12.self_attn*",
182
+ "model.layers.13.self_attn*",
183
+ "model.layers.14.self_attn*",
184
+ "model.layers.15.self_attn*",
185
+ "model.layers.16.self_attn*",
186
+ "model.layers.17.self_attn*",
187
+ "model.layers.18.self_attn*",
188
+ "model.layers.19.self_attn*",
189
+ "model.layers.2.self_attn*",
190
+ "model.layers.20.self_attn*",
191
+ "model.layers.21.self_attn*",
192
+ "model.layers.22.self_attn*",
193
+ "model.layers.23.self_attn*",
194
+ "model.layers.24.self_attn*",
195
+ "model.layers.25.self_attn*",
196
+ "model.layers.26.self_attn*",
197
+ "model.layers.27.self_attn*",
198
+ "model.layers.28.self_attn*",
199
+ "model.layers.29.self_attn*",
200
+ "model.layers.3.self_attn*",
201
+ "model.layers.30.self_attn*",
202
+ "model.layers.31.self_attn*",
203
+ "model.layers.32.self_attn*",
204
+ "model.layers.33.self_attn*",
205
+ "model.layers.34.self_attn*",
206
+ "model.layers.35.self_attn*",
207
+ "model.layers.36.self_attn*",
208
+ "model.layers.37.self_attn*",
209
+ "model.layers.38.self_attn*",
210
+ "model.layers.39.self_attn*",
211
+ "model.layers.4.self_attn*",
212
+ "model.layers.40.self_attn*",
213
+ "model.layers.41.self_attn*",
214
+ "model.layers.42.self_attn*",
215
+ "model.layers.43.self_attn*",
216
+ "model.layers.44.self_attn*",
217
+ "model.layers.45.self_attn*",
218
+ "model.layers.46.self_attn*",
219
+ "model.layers.47.self_attn*",
220
+ "model.layers.48.self_attn*",
221
+ "model.layers.49.self_attn*",
222
+ "model.layers.5.self_attn*",
223
+ "model.layers.50.self_attn*",
224
+ "model.layers.51.self_attn*",
225
+ "model.layers.52.self_attn*",
226
+ "model.layers.53.self_attn*",
227
+ "model.layers.54.self_attn*",
228
+ "model.layers.55.self_attn*",
229
+ "model.layers.56.self_attn*",
230
+ "model.layers.57.self_attn*",
231
+ "model.layers.58.self_attn*",
232
+ "model.layers.59.self_attn*",
233
+ "model.layers.6.self_attn*",
234
+ "model.layers.60.self_attn*",
235
+ "model.layers.61.self_attn*",
236
+ "model.layers.62.self_attn*",
237
+ "model.layers.63.self_attn*",
238
+ "model.layers.64.self_attn*",
239
+ "model.layers.65.self_attn*",
240
+ "model.layers.66.self_attn*",
241
+ "model.layers.67.self_attn*",
242
+ "model.layers.68.self_attn*",
243
+ "model.layers.69.self_attn*",
244
+ "model.layers.7.self_attn*",
245
+ "model.layers.70.self_attn*",
246
+ "model.layers.71.self_attn*",
247
+ "model.layers.72.self_attn*",
248
+ "model.layers.73.self_attn*",
249
+ "model.layers.74.self_attn*",
250
+ "model.layers.75.self_attn*",
251
+ "model.layers.76.self_attn*",
252
+ "model.layers.77.self_attn*",
253
+ "model.layers.8.self_attn*",
254
+ "model.layers.9.self_attn*"
255
+ ],
256
+ "quant_algo": "NVFP4",
257
+ "kv_cache_scheme": {
258
+ "dynamic": false,
259
+ "num_bits": 8,
260
+ "type": "float"
261
+ },
262
+ "producer": {
263
+ "name": "modelopt",
264
+ "version": "0.39.0.dev290+gf9d9a71de.d20260214"
265
+ },
266
+ "quant_method": "modelopt"
267
+ }
268
+ }
generation_config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": null,
3
+ "max_new_tokens": null,
4
+ "min_length": null,
5
+ "min_new_tokens": null,
6
+ "early_stopping": null,
7
+ "max_time": null,
8
+ "stop_strings": null,
9
+ "do_sample": null,
10
+ "num_beams": null,
11
+ "use_cache": true,
12
+ "cache_implementation": null,
13
+ "cache_config": null,
14
+ "temperature": null,
15
+ "top_k": null,
16
+ "top_p": null,
17
+ "min_p": null,
18
+ "top_h": null,
19
+ "typical_p": null,
20
+ "epsilon_cutoff": null,
21
+ "eta_cutoff": null,
22
+ "repetition_penalty": null,
23
+ "encoder_repetition_penalty": null,
24
+ "length_penalty": null,
25
+ "no_repeat_ngram_size": null,
26
+ "bad_words_ids": null,
27
+ "renormalize_logits": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "remove_invalid_values": null,
31
+ "exponential_decay_length_penalty": null,
32
+ "suppress_tokens": null,
33
+ "begin_suppress_tokens": null,
34
+ "sequence_bias": null,
35
+ "token_healing": null,
36
+ "guidance_scale": null,
37
+ "watermarking_config": null,
38
+ "num_return_sequences": null,
39
+ "output_attentions": false,
40
+ "output_hidden_states": false,
41
+ "output_scores": null,
42
+ "output_logits": null,
43
+ "return_dict_in_generate": null,
44
+ "pad_token_id": 154820,
45
+ "bos_token_id": 0,
46
+ "eos_token_id": [
47
+ 154820,
48
+ 154827,
49
+ 154829
50
+ ],
51
+ "encoder_no_repeat_ngram_size": null,
52
+ "decoder_start_token_id": null,
53
+ "is_assistant": null,
54
+ "num_assistant_tokens": null,
55
+ "num_assistant_tokens_schedule": null,
56
+ "assistant_confidence_threshold": null,
57
+ "prompt_lookup_num_tokens": null,
58
+ "max_matching_ngram_size": null,
59
+ "assistant_early_exit": null,
60
+ "assistant_lookbehind": null,
61
+ "target_lookbehind": null,
62
+ "compile_config": null,
63
+ "disable_compile": null,
64
+ "low_memory": null,
65
+ "penalty_alpha": null,
66
+ "dola_layers": null,
67
+ "diversity_penalty": null,
68
+ "num_beam_groups": null,
69
+ "constraints": null,
70
+ "force_words_ids": null,
71
+ "prefill_chunk_size": null,
72
+ "_from_model_config": true,
73
+ "transformers_version": "5.2.0.dev0"
74
+ }
hf_quant_config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config_groups": {
3
+ "group_0": {
4
+ "input_activations": {
5
+ "dynamic": false,
6
+ "num_bits": 4,
7
+ "type": "float",
8
+ "group_size": 16
9
+ },
10
+ "weights": {
11
+ "dynamic": false,
12
+ "num_bits": 4,
13
+ "type": "float",
14
+ "group_size": 16
15
+ },
16
+ "targets": [
17
+ "Linear"
18
+ ]
19
+ }
20
+ },
21
+ "ignore": [
22
+ "lm_head",
23
+ "model.layers.0.self_attn*",
24
+ "model.layers.1.self_attn*",
25
+ "model.layers.10.self_attn*",
26
+ "model.layers.11.self_attn*",
27
+ "model.layers.12.self_attn*",
28
+ "model.layers.13.self_attn*",
29
+ "model.layers.14.self_attn*",
30
+ "model.layers.15.self_attn*",
31
+ "model.layers.16.self_attn*",
32
+ "model.layers.17.self_attn*",
33
+ "model.layers.18.self_attn*",
34
+ "model.layers.19.self_attn*",
35
+ "model.layers.2.self_attn*",
36
+ "model.layers.20.self_attn*",
37
+ "model.layers.21.self_attn*",
38
+ "model.layers.22.self_attn*",
39
+ "model.layers.23.self_attn*",
40
+ "model.layers.24.self_attn*",
41
+ "model.layers.25.self_attn*",
42
+ "model.layers.26.self_attn*",
43
+ "model.layers.27.self_attn*",
44
+ "model.layers.28.self_attn*",
45
+ "model.layers.29.self_attn*",
46
+ "model.layers.3.self_attn*",
47
+ "model.layers.30.self_attn*",
48
+ "model.layers.31.self_attn*",
49
+ "model.layers.32.self_attn*",
50
+ "model.layers.33.self_attn*",
51
+ "model.layers.34.self_attn*",
52
+ "model.layers.35.self_attn*",
53
+ "model.layers.36.self_attn*",
54
+ "model.layers.37.self_attn*",
55
+ "model.layers.38.self_attn*",
56
+ "model.layers.39.self_attn*",
57
+ "model.layers.4.self_attn*",
58
+ "model.layers.40.self_attn*",
59
+ "model.layers.41.self_attn*",
60
+ "model.layers.42.self_attn*",
61
+ "model.layers.43.self_attn*",
62
+ "model.layers.44.self_attn*",
63
+ "model.layers.45.self_attn*",
64
+ "model.layers.46.self_attn*",
65
+ "model.layers.47.self_attn*",
66
+ "model.layers.48.self_attn*",
67
+ "model.layers.49.self_attn*",
68
+ "model.layers.5.self_attn*",
69
+ "model.layers.50.self_attn*",
70
+ "model.layers.51.self_attn*",
71
+ "model.layers.52.self_attn*",
72
+ "model.layers.53.self_attn*",
73
+ "model.layers.54.self_attn*",
74
+ "model.layers.55.self_attn*",
75
+ "model.layers.56.self_attn*",
76
+ "model.layers.57.self_attn*",
77
+ "model.layers.58.self_attn*",
78
+ "model.layers.59.self_attn*",
79
+ "model.layers.6.self_attn*",
80
+ "model.layers.60.self_attn*",
81
+ "model.layers.61.self_attn*",
82
+ "model.layers.62.self_attn*",
83
+ "model.layers.63.self_attn*",
84
+ "model.layers.64.self_attn*",
85
+ "model.layers.65.self_attn*",
86
+ "model.layers.66.self_attn*",
87
+ "model.layers.67.self_attn*",
88
+ "model.layers.68.self_attn*",
89
+ "model.layers.69.self_attn*",
90
+ "model.layers.7.self_attn*",
91
+ "model.layers.70.self_attn*",
92
+ "model.layers.71.self_attn*",
93
+ "model.layers.72.self_attn*",
94
+ "model.layers.73.self_attn*",
95
+ "model.layers.74.self_attn*",
96
+ "model.layers.75.self_attn*",
97
+ "model.layers.76.self_attn*",
98
+ "model.layers.77.self_attn*",
99
+ "model.layers.8.self_attn*",
100
+ "model.layers.9.self_attn*"
101
+ ],
102
+ "quant_algo": "NVFP4",
103
+ "kv_cache_scheme": {
104
+ "dynamic": false,
105
+ "num_bits": 8,
106
+ "type": "float"
107
+ },
108
+ "producer": {
109
+ "name": "modelopt",
110
+ "version": "0.39.0.dev290+gf9d9a71de.d20260214"
111
+ },
112
+ "quant_method": "modelopt"
113
+ }
model-00006-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf0d4bcd9dbfce7ec8c3e5d66555e14af08b22c0db838b4c7390eb65a8082d0
3
+ size 5370444876
model-00008-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c1ae9966ce076bc7df12bda8e0eb7e55b6fa00534b5c5867967463c6f9bf476
3
+ size 5370445148
model-00011-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cca2a6f13e5a665fb02300f4642c86bd80aa78a6af36a6f92637ecc4ab9677a
3
+ size 5373591688
model-00014-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:813570148a55a9d8ca3ec73b750a8af570324baa4f1edf37515a530da35c812a
3
+ size 5370447300
model-00016-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67135f17a9856cc541d9f72f829a794ed4d37f81d51ae64886bda80702eccd9
3
+ size 5370447356
model-00019-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a399d0b87c4f5c7ff8cf3de93816cb0c09c58451390d0cda8a39f3d1f93063
3
+ size 5370447172
model-00021-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35dd921d300af6d06d2294f6a00e38846180b45d62042569a91e324cd8c8cec6
3
+ size 5370447012
model-00022-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45c0c9edc6a6703b03a7292a441fefeb7b89d36bc3c00500df96a161d41353f
3
+ size 5370447164
model-00023-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70abd450ad1bdd6f8ed13dbb34916a89d20992f06f1ab5c80e156a2d59a70223
3
+ size 5369540220
model-00025-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5b0fac18528bc126ba02183140e7ccf212182b60de754cabad1a397adc3893
3
+ size 5370447388
model-00026-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a0e0f3258aad710f03477858d6b4453c90dce2205b8786a4dbe007ee18de3a
3
+ size 5370447300
model-00027-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff6cdb0c15b83ecd70dfbfecd4766d5abb210bc7cb1699d8baf697c4fc2adef
3
+ size 5370447324
model-00030-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d144ff87884f1e07872cf64e484a238d450880a0d62ca34e8cc7195b2c7d0e0
3
+ size 5370447364
model-00031-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93747f976cd0025158de3d433d721e15e6189b8200b9df2c9dbf3d5815e0b84b
3
+ size 5370447540
model-00034-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb4aa2bbd6b4db60f868a0c539d39625326aff603fb89cb149ac2675188fe7a
3
+ size 5370446980
model-00035-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee382e72a8d58c718a97415aa1d4aa77c058f4d053e632f0c9b7e4ed0866b30
3
+ size 5370447156
model-00036-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:446bb068a54ad9559690b5e0e518e86e879c15451fd90b9ac5142ab7e55ceb91
3
+ size 5494054480
model-00037-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5c10072e987ac18e15dffd3a490cca0257d4a7f86b6fa902d6c0a66eb38019
3
+ size 5369121324
model-00038-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6641f3ad26229e26f7bd58a944ba28c15d5fb960cb9a4bb694ee1a3e44c90b
3
+ size 5370447476
model-00039-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d734199f744ebb997b829dbe98a13ab2794738459cbb984ff8f9d4c9f7cb90b1
3
+ size 5370447332
model-00042-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60015ca9b3179ef34f33a9082149e2ebe523557622ded864a81f6bb829ed8aac
3
+ size 5370447356
model-00044-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f2ffc115d7c9a4765efcd80291187d1cfa240335be662d14b725c79573b83ef
3
+ size 5370447460
model-00046-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9024a5d81487f80da262b837956c7122330645a11b86d185e8be56245ac5e6b
3
+ size 5370447020
model-00048-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ded23696367b82e9a674fab7824d72306da787f98645af00aa6b17811354b1
3
+ size 5370447060
model-00049-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ac7f19901d6663f5b8c2484286d4a988dae15be92c5a625a7b445e862c3a5ff
3
+ size 5370447164
model-00050-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b908325b29e44afcab5f8cf228108da0457d8901a96eec89e0947157c9ce61c
3
+ size 5369253496
model-00051-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad40fada34a84990e74430c02d54eed57934419aeedc2421bf848dcf0e755a85
3
+ size 5373591688
model-00052-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c38718568ebb086e98351234d050b5974557496b035f0150fae7080dc1229ae8
3
+ size 5370447356
model-00053-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df5ca7217f0879dfb56770dbb9bdf9c11733fe3214928320c03ec4a1be369eb
3
+ size 5370447316
model-00054-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61f16bcc75e5ddfde30b64bec3a98e17f322a5b2fcf6a6ff6c5e60c2a2971b25
3
+ size 5370447300
model-00056-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c2c139ad7da33b9532d1560ffd5446158bc02032d56c26531e7722bc655576
3
+ size 5370447356
model-00057-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8defeb5f87ad1d08c1cf10640169ca5ee05e5e05f8567b53264d679938843824
3
+ size 5370447412
model-00058-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bcd9e6b06be11a6b38f809ac54093145418286859389c1f1589cf6abbec19b9
3
+ size 5370447540
model-00059-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8386711a9f257018c0b0cacf06172563709123781641811f466ff72795c7df34
3
+ size 5370447172
model-00060-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da7dddc1577a70a0b52b1d2729ea84ccd468efc5bd739dc2611fd553fce4cb2c
3
+ size 5370446980
model-00062-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b38a81ebf36df5726c64d16b57e9af92357271feabc64f28bfdcd81fc128926f
3
+ size 5370447164
model-00064-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76dd5a6d6236474e4900118d2426376dc37428c02a996c77de216f2771e5ae4
3
+ size 5373305276
model-00065-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17c4e89b00b8144532cb4505ff86ed04f7756a41f2960a113a753a473cc2b0e7
3
+ size 5370447388
model-00066-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a3893ed239fded2810effe741c3744f8eafd44513018cb580cb2c55f908878
3
+ size 5370447300
model-00070-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21e143a3cd6004fc1164fac0430b5011445a7fe1da9496cfa29efd3deddb53d
3
+ size 5370447364
model-00071-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09eb81430c07121a40bb7361a8f4ed0c940179b51f2d59f63d13e90296656bdd
3
+ size 5370447540
model-00073-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0234a6d4c9c0ad9b45a33e8a365f8ef4ff98039fb62efb94cc73705e82e03f3
3
+ size 5370446980
model-00076-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e51da96c5b0f3f75cab1a9d4d99699880bbcf76f0b469fdc327f08d74716658
3
+ size 5494054480
model-00078-of-00082.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:679fa7e23699e7c2b13db531668f9af89fef5a8c738b1566a38d55e0123f05d9
3
+ size 5370447476
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
3
+ size 20217442