rodrigoramosrs/veriloop-coder-e2-nvfp4
2
1{
2 "architectures": [
3 "Qwen3_5ForCausalLM"
4 ],
5 "attention_bias": false,
6 "attention_dropout": 0.0,
7 "attn_output_gate": true,
8 "bos_token_id": 248044,
9 "dtype": "bfloat16",
10 "eos_token_id": 248044,
11 "full_attention_interval": 4,
12 "head_dim": 256,
13 "hidden_act": "silu",
14 "hidden_size": 5120,
15 "initializer_range": 0.02,
16 "intermediate_size": 17408,
17 "layer_types": [
18 "linear_attention",
19 "linear_attention",
20 "linear_attention",
21 "full_attention",
22 "linear_attention",
23 "linear_attention",
24 "linear_attention",
25 "full_attention",
26 "linear_attention",
27 "linear_attention",
28 "linear_attention",
29 "full_attention",
30 "linear_attention",
31 "linear_attention",
32 "linear_attention",
33 "full_attention",
34 "linear_attention",
35 "linear_attention",
36 "linear_attention",
37 "full_attention",
38 "linear_attention",
39 "linear_attention",
40 "linear_attention",
41 "full_attention",
42 "linear_attention",
43 "linear_attention",
44 "linear_attention",
45 "full_attention",
46 "linear_attention",
47 "linear_attention",
48 "linear_attention",
49 "full_attention",
50 "linear_attention",
51 "linear_attention",
52 "linear_attention",
53 "full_attention",
54 "linear_attention",
55 "linear_attention",
56 "linear_attention",
57 "full_attention",
58 "linear_attention",
59 "linear_attention",
60 "linear_attention",
61 "full_attention",
62 "linear_attention",
63 "linear_attention",
64 "linear_attention",
65 "full_attention",
66 "linear_attention",
67 "linear_attention",
68 "linear_attention",
69 "full_attention",
70 "linear_attention",
71 "linear_attention",
72 "linear_attention",
73 "full_attention",
74 "linear_attention",
75 "linear_attention",
76 "linear_attention",
77 "full_attention",
78 "linear_attention",
79 "linear_attention",
80 "linear_attention",
81 "full_attention"
82 ],
83 "linear_conv_kernel_dim": 4,
84 "linear_key_head_dim": 128,
85 "linear_num_key_heads": 16,
86 "linear_num_value_heads": 48,
87 "linear_value_head_dim": 128,
88 "mamba_ssm_dtype": "float32",
89 "max_position_embeddings": 262144,
90 "model_type": "qwen3_5_text",
91 "mtp_num_hidden_layers": 1,
92 "mtp_use_dedicated_embeddings": false,
93 "num_attention_heads": 24,
94 "num_hidden_layers": 64,
95 "num_key_value_heads": 4,
96 "output_gate_type": "swish",
97 "pad_token_id": null,
98 "partial_rotary_factor": 0.25,
99 "rms_norm_eps": 1e-06,
100 "rope_parameters": {
101 "mrope_interleaved": true,
102 "mrope_section": [
103 11,
104 11,
105 10
106 ],
107 "partial_rotary_factor": 0.25,
108 "rope_theta": 10000000,
109 "rope_type": "default"
110 },
111 "tie_word_embeddings": false,
112 "transformers_version": "5.14.1",
113 "use_cache": false,
114 "vocab_size": 248320,
115 "quantization_config": {
116 "config_groups": {
117 "group_0": {
118 "input_activations": {
119 "dynamic": false,
120 "num_bits": 4,
121 "type": "float",
122 "group_size": 16
123 },
124 "weights": {
125 "dynamic": false,
126 "num_bits": 4,
127 "type": "float",
128 "group_size": 16
129 },
130 "targets": [
131 "Linear"
132 ]
133 }
134 },
135 "ignore": [
136 "lm_head",
137 "model.language_model.embed_tokens",
138 "model.language_model.layers.0.linear_attn.conv1d",
139 "model.language_model.layers.0.linear_attn.in_proj_a",
140 "model.language_model.layers.0.linear_attn.in_proj_b",
141 "model.language_model.layers.1.linear_attn.conv1d",
142 "model.language_model.layers.1.linear_attn.in_proj_a",
143 "model.language_model.layers.1.linear_attn.in_proj_b",
144 "model.language_model.layers.10.linear_attn.conv1d",
145 "model.language_model.layers.10.linear_attn.in_proj_a",
146 "model.language_model.layers.10.linear_attn.in_proj_b",
147 "model.language_model.layers.12.linear_attn.conv1d",
148 "model.language_model.layers.12.linear_attn.in_proj_a",
149 "model.language_model.layers.12.linear_attn.in_proj_b",
150 "model.language_model.layers.13.linear_attn.conv1d",
151 "model.language_model.layers.13.linear_attn.in_proj_a",
152 "model.language_model.layers.13.linear_attn.in_proj_b",
153 "model.language_model.layers.14.linear_attn.conv1d",
154 "model.language_model.layers.14.linear_attn.in_proj_a",
155 "model.language_model.layers.14.linear_attn.in_proj_b",
156 "model.language_model.layers.16.linear_attn.conv1d",
157 "model.language_model.layers.16.linear_attn.in_proj_a",
158 "model.language_model.layers.16.linear_attn.in_proj_b",
159 "model.language_model.layers.17.linear_attn.conv1d",
160 "model.language_model.layers.17.linear_attn.in_proj_a",
161 "model.language_model.layers.17.linear_attn.in_proj_b",
162 "model.language_model.layers.18.linear_attn.conv1d",
163 "model.language_model.layers.18.linear_attn.in_proj_a",
164 "model.language_model.layers.18.linear_attn.in_proj_b",
165 "model.language_model.layers.2.linear_attn.conv1d",
166 "model.language_model.layers.2.linear_attn.in_proj_a",
167 "model.language_model.layers.2.linear_attn.in_proj_b",
168 "model.language_model.layers.20.linear_attn.conv1d",
169 "model.language_model.layers.20.linear_attn.in_proj_a",
170 "model.language_model.layers.20.linear_attn.in_proj_b",
171 "model.language_model.layers.21.linear_attn.conv1d",
172 "model.language_model.layers.21.linear_attn.in_proj_a",
173 "model.language_model.layers.21.linear_attn.in_proj_b",
174 "model.language_model.layers.22.linear_attn.conv1d",
175 "model.language_model.layers.22.linear_attn.in_proj_a",
176 "model.language_model.layers.22.linear_attn.in_proj_b",
177 "model.language_model.layers.24.linear_attn.conv1d",
178 "model.language_model.layers.24.linear_attn.in_proj_a",
179 "model.language_model.layers.24.linear_attn.in_proj_b",
180 "model.language_model.layers.25.linear_attn.conv1d",
181 "model.language_model.layers.25.linear_attn.in_proj_a",
182 "model.language_model.layers.25.linear_attn.in_proj_b",
183 "model.language_model.layers.26.linear_attn.conv1d",
184 "model.language_model.layers.26.linear_attn.in_proj_a",
185 "model.language_model.layers.26.linear_attn.in_proj_b",
186 "model.language_model.layers.28.linear_attn.conv1d",
187 "model.language_model.layers.28.linear_attn.in_proj_a",
188 "model.language_model.layers.28.linear_attn.in_proj_b",
189 "model.language_model.layers.29.linear_attn.conv1d",
190 "model.language_model.layers.29.linear_attn.in_proj_a",
191 "model.language_model.layers.29.linear_attn.in_proj_b",
192 "model.language_model.layers.30.linear_attn.conv1d",
193 "model.language_model.layers.30.linear_attn.in_proj_a",
194 "model.language_model.layers.30.linear_attn.in_proj_b",
195 "model.language_model.layers.32.linear_attn.conv1d",
196 "model.language_model.layers.32.linear_attn.in_proj_a",
197 "model.language_model.layers.32.linear_attn.in_proj_b",
198 "model.language_model.layers.33.linear_attn.conv1d",
199 "model.language_model.layers.33.linear_attn.in_proj_a",
200 "model.language_model.layers.33.linear_attn.in_proj_b",
201 "model.language_model.layers.34.linear_attn.conv1d",
202 "model.language_model.layers.34.linear_attn.in_proj_a",
203 "model.language_model.layers.34.linear_attn.in_proj_b",
204 "model.language_model.layers.36.linear_attn.conv1d",
205 "model.language_model.layers.36.linear_attn.in_proj_a",
206 "model.language_model.layers.36.linear_attn.in_proj_b",
207 "model.language_model.layers.37.linear_attn.conv1d",
208 "model.language_model.layers.37.linear_attn.in_proj_a",
209 "model.language_model.layers.37.linear_attn.in_proj_b",
210 "model.language_model.layers.38.linear_attn.conv1d",
211 "model.language_model.layers.38.linear_attn.in_proj_a",
212 "model.language_model.layers.38.linear_attn.in_proj_b",
213 "model.language_model.layers.4.linear_attn.conv1d",
214 "model.language_model.layers.4.linear_attn.in_proj_a",
215 "model.language_model.layers.4.linear_attn.in_proj_b",
216 "model.language_model.layers.40.linear_attn.conv1d",
217 "model.language_model.layers.40.linear_attn.in_proj_a",
218 "model.language_model.layers.40.linear_attn.in_proj_b",
219 "model.language_model.layers.41.linear_attn.conv1d",
220 "model.language_model.layers.41.linear_attn.in_proj_a",
221 "model.language_model.layers.41.linear_attn.in_proj_b",
222 "model.language_model.layers.42.linear_attn.conv1d",
223 "model.language_model.layers.42.linear_attn.in_proj_a",
224 "model.language_model.layers.42.linear_attn.in_proj_b",
225 "model.language_model.layers.44.linear_attn.conv1d",
226 "model.language_model.layers.44.linear_attn.in_proj_a",
227 "model.language_model.layers.44.linear_attn.in_proj_b",
228 "model.language_model.layers.45.linear_attn.conv1d",
229 "model.language_model.layers.45.linear_attn.in_proj_a",
230 "model.language_model.layers.45.linear_attn.in_proj_b",
231 "model.language_model.layers.46.linear_attn.conv1d",
232 "model.language_model.layers.46.linear_attn.in_proj_a",
233 "model.language_model.layers.46.linear_attn.in_proj_b",
234 "model.language_model.layers.48.linear_attn.conv1d",
235 "model.language_model.layers.48.linear_attn.in_proj_a",
236 "model.language_model.layers.48.linear_attn.in_proj_b",
237 "model.language_model.layers.49.linear_attn.conv1d",
238 "model.language_model.layers.49.linear_attn.in_proj_a",
239 "model.language_model.layers.49.linear_attn.in_proj_b",
240 "model.language_model.layers.5.linear_attn.conv1d",
241 "model.language_model.layers.5.linear_attn.in_proj_a",
242 "model.language_model.layers.5.linear_attn.in_proj_b",
243 "model.language_model.layers.50.linear_attn.conv1d",
244 "model.language_model.layers.50.linear_attn.in_proj_a",
245 "model.language_model.layers.50.linear_attn.in_proj_b",
246 "model.language_model.layers.52.linear_attn.conv1d",
247 "model.language_model.layers.52.linear_attn.in_proj_a",
248 "model.language_model.layers.52.linear_attn.in_proj_b",
249 "model.language_model.layers.53.linear_attn.conv1d",
250 "model.language_model.layers.53.linear_attn.in_proj_a",
251 "model.language_model.layers.53.linear_attn.in_proj_b",
252 "model.language_model.layers.54.linear_attn.conv1d",
253 "model.language_model.layers.54.linear_attn.in_proj_a",
254 "model.language_model.layers.54.linear_attn.in_proj_b",
255 "model.language_model.layers.56.linear_attn.conv1d",
256 "model.language_model.layers.56.linear_attn.in_proj_a",
257 "model.language_model.layers.56.linear_attn.in_proj_b",
258 "model.language_model.layers.57.linear_attn.conv1d",
259 "model.language_model.layers.57.linear_attn.in_proj_a",
260 "model.language_model.layers.57.linear_attn.in_proj_b",
261 "model.language_model.layers.58.linear_attn.conv1d",
262 "model.language_model.layers.58.linear_attn.in_proj_a",
263 "model.language_model.layers.58.linear_attn.in_proj_b",
264 "model.language_model.layers.6.linear_attn.conv1d",
265 "model.language_model.layers.6.linear_attn.in_proj_a",
266 "model.language_model.layers.6.linear_attn.in_proj_b",
267 "model.language_model.layers.60.linear_attn.conv1d",
268 "model.language_model.layers.60.linear_attn.in_proj_a",
269 "model.language_model.layers.60.linear_attn.in_proj_b",
270 "model.language_model.layers.61.linear_attn.conv1d",
271 "model.language_model.layers.61.linear_attn.in_proj_a",
272 "model.language_model.layers.61.linear_attn.in_proj_b",
273 "model.language_model.layers.62.linear_attn.conv1d",
274 "model.language_model.layers.62.linear_attn.in_proj_a",
275 "model.language_model.layers.62.linear_attn.in_proj_b",
276 "model.language_model.layers.8.linear_attn.conv1d",
277 "model.language_model.layers.8.linear_attn.in_proj_a",
278 "model.language_model.layers.8.linear_attn.in_proj_b",
279 "model.language_model.layers.9.linear_attn.conv1d",
280 "model.language_model.layers.9.linear_attn.in_proj_a",
281 "model.language_model.layers.9.linear_attn.in_proj_b",
282 "model.embed_tokens",
283 "model.layers.0.linear_attn.conv1d",
284 "model.layers.0.linear_attn.in_proj_a",
285 "model.layers.0.linear_attn.in_proj_b",
286 "model.layers.1.linear_attn.conv1d",
287 "model.layers.1.linear_attn.in_proj_a",
288 "model.layers.1.linear_attn.in_proj_b",
289 "model.layers.10.linear_attn.conv1d",
290 "model.layers.10.linear_attn.in_proj_a",
291 "model.layers.10.linear_attn.in_proj_b",
292 "model.layers.12.linear_attn.conv1d",
293 "model.layers.12.linear_attn.in_proj_a",
294 "model.layers.12.linear_attn.in_proj_b",
295 "model.layers.13.linear_attn.conv1d",
296 "model.layers.13.linear_attn.in_proj_a",
297 "model.layers.13.linear_attn.in_proj_b",
298 "model.layers.14.linear_attn.conv1d",
299 "model.layers.14.linear_attn.in_proj_a",
300 "model.layers.14.linear_attn.in_proj_b",
301 "model.layers.16.linear_attn.conv1d",
302 "model.layers.16.linear_attn.in_proj_a",
303 "model.layers.16.linear_attn.in_proj_b",
304 "model.layers.17.linear_attn.conv1d",
305 "model.layers.17.linear_attn.in_proj_a",
306 "model.layers.17.linear_attn.in_proj_b",
307 "model.layers.18.linear_attn.conv1d",
308 "model.layers.18.linear_attn.in_proj_a",
309 "model.layers.18.linear_attn.in_proj_b",
310 "model.layers.2.linear_attn.conv1d",
311 "model.layers.2.linear_attn.in_proj_a",
312 "model.layers.2.linear_attn.in_proj_b",
313 "model.layers.20.linear_attn.conv1d",
314 "model.layers.20.linear_attn.in_proj_a",
315 "model.layers.20.linear_attn.in_proj_b",
316 "model.layers.21.linear_attn.conv1d",
317 "model.layers.21.linear_attn.in_proj_a",
318 "model.layers.21.linear_attn.in_proj_b",
319 "model.layers.22.linear_attn.conv1d",
320 "model.layers.22.linear_attn.in_proj_a",
321 "model.layers.22.linear_attn.in_proj_b",
322 "model.layers.24.linear_attn.conv1d",
323 "model.layers.24.linear_attn.in_proj_a",
324 "model.layers.24.linear_attn.in_proj_b",
325 "model.layers.25.linear_attn.conv1d",
326 "model.layers.25.linear_attn.in_proj_a",
327 "model.layers.25.linear_attn.in_proj_b",
328 "model.layers.26.linear_attn.conv1d",
329 "model.layers.26.linear_attn.in_proj_a",
330 "model.layers.26.linear_attn.in_proj_b",
331 "model.layers.28.linear_attn.conv1d",
332 "model.layers.28.linear_attn.in_proj_a",
333 "model.layers.28.linear_attn.in_proj_b",
334 "model.layers.29.linear_attn.conv1d",
335 "model.layers.29.linear_attn.in_proj_a",
336 "model.layers.29.linear_attn.in_proj_b",
337 "model.layers.30.linear_attn.conv1d",
338 "model.layers.30.linear_attn.in_proj_a",
339 "model.layers.30.linear_attn.in_proj_b",
340 "model.layers.32.linear_attn.conv1d",
341 "model.layers.32.linear_attn.in_proj_a",
342 "model.layers.32.linear_attn.in_proj_b",
343 "model.layers.33.linear_attn.conv1d",
344 "model.layers.33.linear_attn.in_proj_a",
345 "model.layers.33.linear_attn.in_proj_b",
346 "model.layers.34.linear_attn.conv1d",
347 "model.layers.34.linear_attn.in_proj_a",
348 "model.layers.34.linear_attn.in_proj_b",
349 "model.layers.36.linear_attn.conv1d",
350 "model.layers.36.linear_attn.in_proj_a",
351 "model.layers.36.linear_attn.in_proj_b",
352 "model.layers.37.linear_attn.conv1d",
353 "model.layers.37.linear_attn.in_proj_a",
354 "model.layers.37.linear_attn.in_proj_b",
355 "model.layers.38.linear_attn.conv1d",
356 "model.layers.38.linear_attn.in_proj_a",
357 "model.layers.38.linear_attn.in_proj_b",
358 "model.layers.4.linear_attn.conv1d",
359 "model.layers.4.linear_attn.in_proj_a",
360 "model.layers.4.linear_attn.in_proj_b",
361 "model.layers.40.linear_attn.conv1d",
362 "model.layers.40.linear_attn.in_proj_a",
363 "model.layers.40.linear_attn.in_proj_b",
364 "model.layers.41.linear_attn.conv1d",
365 "model.layers.41.linear_attn.in_proj_a",
366 "model.layers.41.linear_attn.in_proj_b",
367 "model.layers.42.linear_attn.conv1d",
368 "model.layers.42.linear_attn.in_proj_a",
369 "model.layers.42.linear_attn.in_proj_b",
370 "model.layers.44.linear_attn.conv1d",
371 "model.layers.44.linear_attn.in_proj_a",
372 "model.layers.44.linear_attn.in_proj_b",
373 "model.layers.45.linear_attn.conv1d",
374 "model.layers.45.linear_attn.in_proj_a",
375 "model.layers.45.linear_attn.in_proj_b",
376 "model.layers.46.linear_attn.conv1d",
377 "model.layers.46.linear_attn.in_proj_a",
378 "model.layers.46.linear_attn.in_proj_b",
379 "model.layers.48.linear_attn.conv1d",
380 "model.layers.48.linear_attn.in_proj_a",
381 "model.layers.48.linear_attn.in_proj_b",
382 "model.layers.49.linear_attn.conv1d",
383 "model.layers.49.linear_attn.in_proj_a",
384 "model.layers.49.linear_attn.in_proj_b",
385 "model.layers.5.linear_attn.conv1d",
386 "model.layers.5.linear_attn.in_proj_a",
387 "model.layers.5.linear_attn.in_proj_b",
388 "model.layers.50.linear_attn.conv1d",
389 "model.layers.50.linear_attn.in_proj_a",
390 "model.layers.50.linear_attn.in_proj_b",
391 "model.layers.52.linear_attn.conv1d",
392 "model.layers.52.linear_attn.in_proj_a",
393 "model.layers.52.linear_attn.in_proj_b",
394 "model.layers.53.linear_attn.conv1d",
395 "model.layers.53.linear_attn.in_proj_a",
396 "model.layers.53.linear_attn.in_proj_b",
397 "model.layers.54.linear_attn.conv1d",
398 "model.layers.54.linear_attn.in_proj_a",
399 "model.layers.54.linear_attn.in_proj_b",
400 "model.layers.56.linear_attn.conv1d",
401 "model.layers.56.linear_attn.in_proj_a",
402 "model.layers.56.linear_attn.in_proj_b",
403 "model.layers.57.linear_attn.conv1d",
404 "model.layers.57.linear_attn.in_proj_a",
405 "model.layers.57.linear_attn.in_proj_b",
406 "model.layers.58.linear_attn.conv1d",
407 "model.layers.58.linear_attn.in_proj_a",
408 "model.layers.58.linear_attn.in_proj_b",
409 "model.layers.6.linear_attn.conv1d",
410 "model.layers.6.linear_attn.in_proj_a",
411 "model.layers.6.linear_attn.in_proj_b",
412 "model.layers.60.linear_attn.conv1d",
413 "model.layers.60.linear_attn.in_proj_a",
414 "model.layers.60.linear_attn.in_proj_b",
415 "model.layers.61.linear_attn.conv1d",
416 "model.layers.61.linear_attn.in_proj_a",
417 "model.layers.61.linear_attn.in_proj_b",
418 "model.layers.62.linear_attn.conv1d",
419 "model.layers.62.linear_attn.in_proj_a",
420 "model.layers.62.linear_attn.in_proj_b",
421 "model.layers.8.linear_attn.conv1d",
422 "model.layers.8.linear_attn.in_proj_a",
423 "model.layers.8.linear_attn.in_proj_b",
424 "model.layers.9.linear_attn.conv1d",
425 "model.layers.9.linear_attn.in_proj_a",
426 "model.layers.9.linear_attn.in_proj_b",
427 "model.layers.0.linear_attn.in_proj_ba",
428 "model.language_model.layers.0.linear_attn.in_proj_ba",
429 "model.layers.1.linear_attn.in_proj_ba",
430 "model.language_model.layers.1.linear_attn.in_proj_ba",
431 "model.layers.2.linear_attn.in_proj_ba",
432 "model.language_model.layers.2.linear_attn.in_proj_ba",
433 "model.layers.4.linear_attn.in_proj_ba",
434 "model.language_model.layers.4.linear_attn.in_proj_ba",
435 "model.layers.5.linear_attn.in_proj_ba",
436 "model.language_model.layers.5.linear_attn.in_proj_ba",
437 "model.layers.6.linear_attn.in_proj_ba",
438 "model.language_model.layers.6.linear_attn.in_proj_ba",
439 "model.layers.8.linear_attn.in_proj_ba",
440 "model.language_model.layers.8.linear_attn.in_proj_ba",
441 "model.layers.9.linear_attn.in_proj_ba",
442 "model.language_model.layers.9.linear_attn.in_proj_ba",
443 "model.layers.10.linear_attn.in_proj_ba",
444 "model.language_model.layers.10.linear_attn.in_proj_ba",
445 "model.layers.12.linear_attn.in_proj_ba",
446 "model.language_model.layers.12.linear_attn.in_proj_ba",
447 "model.layers.13.linear_attn.in_proj_ba",
448 "model.language_model.layers.13.linear_attn.in_proj_ba",
449 "model.layers.14.linear_attn.in_proj_ba",
450 "model.language_model.layers.14.linear_attn.in_proj_ba",
451 "model.layers.16.linear_attn.in_proj_ba",
452 "model.language_model.layers.16.linear_attn.in_proj_ba",
453 "model.layers.17.linear_attn.in_proj_ba",
454 "model.language_model.layers.17.linear_attn.in_proj_ba",
455 "model.layers.18.linear_attn.in_proj_ba",
456 "model.language_model.layers.18.linear_attn.in_proj_ba",
457 "model.layers.20.linear_attn.in_proj_ba",
458 "model.language_model.layers.20.linear_attn.in_proj_ba",
459 "model.layers.21.linear_attn.in_proj_ba",
460 "model.language_model.layers.21.linear_attn.in_proj_ba",
461 "model.layers.22.linear_attn.in_proj_ba",
462 "model.language_model.layers.22.linear_attn.in_proj_ba",
463 "model.layers.24.linear_attn.in_proj_ba",
464 "model.language_model.layers.24.linear_attn.in_proj_ba",
465 "model.layers.25.linear_attn.in_proj_ba",
466 "model.language_model.layers.25.linear_attn.in_proj_ba",
467 "model.layers.26.linear_attn.in_proj_ba",
468 "model.language_model.layers.26.linear_attn.in_proj_ba",
469 "model.layers.28.linear_attn.in_proj_ba",
470 "model.language_model.layers.28.linear_attn.in_proj_ba",
471 "model.layers.29.linear_attn.in_proj_ba",
472 "model.language_model.layers.29.linear_attn.in_proj_ba",
473 "model.layers.30.linear_attn.in_proj_ba",
474 "model.language_model.layers.30.linear_attn.in_proj_ba",
475 "model.layers.32.linear_attn.in_proj_ba",
476 "model.language_model.layers.32.linear_attn.in_proj_ba",
477 "model.layers.33.linear_attn.in_proj_ba",
478 "model.language_model.layers.33.linear_attn.in_proj_ba",
479 "model.layers.34.linear_attn.in_proj_ba",
480 "model.language_model.layers.34.linear_attn.in_proj_ba",
481 "model.layers.36.linear_attn.in_proj_ba",
482 "model.language_model.layers.36.linear_attn.in_proj_ba",
483 "model.layers.37.linear_attn.in_proj_ba",
484 "model.language_model.layers.37.linear_attn.in_proj_ba",
485 "model.layers.38.linear_attn.in_proj_ba",
486 "model.language_model.layers.38.linear_attn.in_proj_ba",
487 "model.layers.40.linear_attn.in_proj_ba",
488 "model.language_model.layers.40.linear_attn.in_proj_ba",
489 "model.layers.41.linear_attn.in_proj_ba",
490 "model.language_model.layers.41.linear_attn.in_proj_ba",
491 "model.layers.42.linear_attn.in_proj_ba",
492 "model.language_model.layers.42.linear_attn.in_proj_ba",
493 "model.layers.44.linear_attn.in_proj_ba",
494 "model.language_model.layers.44.linear_attn.in_proj_ba",
495 "model.layers.45.linear_attn.in_proj_ba",
496 "model.language_model.layers.45.linear_attn.in_proj_ba",
497 "model.layers.46.linear_attn.in_proj_ba",
498 "model.language_model.layers.46.linear_attn.in_proj_ba",
499 "model.layers.48.linear_attn.in_proj_ba",
500 "model.language_model.layers.48.linear_attn.in_proj_ba",
501 "model.layers.49.linear_attn.in_proj_ba",
502 "model.language_model.layers.49.linear_attn.in_proj_ba",
503 "model.layers.50.linear_attn.in_proj_ba",
504 "model.language_model.layers.50.linear_attn.in_proj_ba",
505 "model.layers.52.linear_attn.in_proj_ba",
506 "model.language_model.layers.52.linear_attn.in_proj_ba",
507 "model.layers.53.linear_attn.in_proj_ba",
508 "model.language_model.layers.53.linear_attn.in_proj_ba",
509 "model.layers.54.linear_attn.in_proj_ba",
510 "model.language_model.layers.54.linear_attn.in_proj_ba",
511 "model.layers.56.linear_attn.in_proj_ba",
512 "model.language_model.layers.56.linear_attn.in_proj_ba",
513 "model.layers.57.linear_attn.in_proj_ba",
514 "model.language_model.layers.57.linear_attn.in_proj_ba",
515 "model.layers.58.linear_attn.in_proj_ba",
516 "model.language_model.layers.58.linear_attn.in_proj_ba",
517 "model.layers.60.linear_attn.in_proj_ba",
518 "model.language_model.layers.60.linear_attn.in_proj_ba",
519 "model.layers.61.linear_attn.in_proj_ba",
520 "model.language_model.layers.61.linear_attn.in_proj_ba",
521 "model.layers.62.linear_attn.in_proj_ba",
522 "model.language_model.layers.62.linear_attn.in_proj_ba"
523 ],
524 "quant_algo": "NVFP4",
525 "producer": {
526 "name": "modelopt",
527 "version": "0.47.0"
528 },
529 "quant_method": "modelopt"
530 }
531}