Training in progress, step 200
Browse files- config.json +851 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +36 -0
- tokenizer.json +0 -0
- tokenizer_config.json +129 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,851 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "yzhuang/llava-falcon-mamba-7B-linear-anyres",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaFalconMambaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 8,
|
7 |
+
"conv_kernel": 4,
|
8 |
+
"eos_token_id": 11,
|
9 |
+
"expand": 16,
|
10 |
+
"freeze_mm_mlp_adapter": false,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 4096,
|
13 |
+
"image_aspect_ratio": "anyres",
|
14 |
+
"image_grid_pinpoints": [
|
15 |
+
[
|
16 |
+
336,
|
17 |
+
336
|
18 |
+
],
|
19 |
+
[
|
20 |
+
336,
|
21 |
+
672
|
22 |
+
],
|
23 |
+
[
|
24 |
+
336,
|
25 |
+
1008
|
26 |
+
],
|
27 |
+
[
|
28 |
+
336,
|
29 |
+
1344
|
30 |
+
],
|
31 |
+
[
|
32 |
+
336,
|
33 |
+
1680
|
34 |
+
],
|
35 |
+
[
|
36 |
+
336,
|
37 |
+
2016
|
38 |
+
],
|
39 |
+
[
|
40 |
+
336,
|
41 |
+
2352
|
42 |
+
],
|
43 |
+
[
|
44 |
+
336,
|
45 |
+
2688
|
46 |
+
],
|
47 |
+
[
|
48 |
+
336,
|
49 |
+
3024
|
50 |
+
],
|
51 |
+
[
|
52 |
+
336,
|
53 |
+
3360
|
54 |
+
],
|
55 |
+
[
|
56 |
+
336,
|
57 |
+
3696
|
58 |
+
],
|
59 |
+
[
|
60 |
+
336,
|
61 |
+
4032
|
62 |
+
],
|
63 |
+
[
|
64 |
+
336,
|
65 |
+
4368
|
66 |
+
],
|
67 |
+
[
|
68 |
+
336,
|
69 |
+
4704
|
70 |
+
],
|
71 |
+
[
|
72 |
+
336,
|
73 |
+
5040
|
74 |
+
],
|
75 |
+
[
|
76 |
+
336,
|
77 |
+
5376
|
78 |
+
],
|
79 |
+
[
|
80 |
+
336,
|
81 |
+
5712
|
82 |
+
],
|
83 |
+
[
|
84 |
+
336,
|
85 |
+
6048
|
86 |
+
],
|
87 |
+
[
|
88 |
+
336,
|
89 |
+
6384
|
90 |
+
],
|
91 |
+
[
|
92 |
+
336,
|
93 |
+
6720
|
94 |
+
],
|
95 |
+
[
|
96 |
+
336,
|
97 |
+
7056
|
98 |
+
],
|
99 |
+
[
|
100 |
+
336,
|
101 |
+
7392
|
102 |
+
],
|
103 |
+
[
|
104 |
+
336,
|
105 |
+
7728
|
106 |
+
],
|
107 |
+
[
|
108 |
+
336,
|
109 |
+
8064
|
110 |
+
],
|
111 |
+
[
|
112 |
+
336,
|
113 |
+
8400
|
114 |
+
],
|
115 |
+
[
|
116 |
+
336,
|
117 |
+
8736
|
118 |
+
],
|
119 |
+
[
|
120 |
+
336,
|
121 |
+
9072
|
122 |
+
],
|
123 |
+
[
|
124 |
+
336,
|
125 |
+
9408
|
126 |
+
],
|
127 |
+
[
|
128 |
+
336,
|
129 |
+
9744
|
130 |
+
],
|
131 |
+
[
|
132 |
+
336,
|
133 |
+
10080
|
134 |
+
],
|
135 |
+
[
|
136 |
+
336,
|
137 |
+
10416
|
138 |
+
],
|
139 |
+
[
|
140 |
+
336,
|
141 |
+
10752
|
142 |
+
],
|
143 |
+
[
|
144 |
+
336,
|
145 |
+
11088
|
146 |
+
],
|
147 |
+
[
|
148 |
+
336,
|
149 |
+
11424
|
150 |
+
],
|
151 |
+
[
|
152 |
+
336,
|
153 |
+
11760
|
154 |
+
],
|
155 |
+
[
|
156 |
+
336,
|
157 |
+
12096
|
158 |
+
],
|
159 |
+
[
|
160 |
+
336,
|
161 |
+
12432
|
162 |
+
],
|
163 |
+
[
|
164 |
+
336,
|
165 |
+
12768
|
166 |
+
],
|
167 |
+
[
|
168 |
+
336,
|
169 |
+
13104
|
170 |
+
],
|
171 |
+
[
|
172 |
+
336,
|
173 |
+
13440
|
174 |
+
],
|
175 |
+
[
|
176 |
+
336,
|
177 |
+
13776
|
178 |
+
],
|
179 |
+
[
|
180 |
+
336,
|
181 |
+
14112
|
182 |
+
],
|
183 |
+
[
|
184 |
+
336,
|
185 |
+
14448
|
186 |
+
],
|
187 |
+
[
|
188 |
+
336,
|
189 |
+
14784
|
190 |
+
],
|
191 |
+
[
|
192 |
+
336,
|
193 |
+
15120
|
194 |
+
],
|
195 |
+
[
|
196 |
+
336,
|
197 |
+
15456
|
198 |
+
],
|
199 |
+
[
|
200 |
+
336,
|
201 |
+
15792
|
202 |
+
],
|
203 |
+
[
|
204 |
+
336,
|
205 |
+
16128
|
206 |
+
],
|
207 |
+
[
|
208 |
+
672,
|
209 |
+
336
|
210 |
+
],
|
211 |
+
[
|
212 |
+
672,
|
213 |
+
672
|
214 |
+
],
|
215 |
+
[
|
216 |
+
672,
|
217 |
+
1008
|
218 |
+
],
|
219 |
+
[
|
220 |
+
672,
|
221 |
+
1344
|
222 |
+
],
|
223 |
+
[
|
224 |
+
672,
|
225 |
+
1680
|
226 |
+
],
|
227 |
+
[
|
228 |
+
672,
|
229 |
+
2016
|
230 |
+
],
|
231 |
+
[
|
232 |
+
672,
|
233 |
+
2352
|
234 |
+
],
|
235 |
+
[
|
236 |
+
672,
|
237 |
+
2688
|
238 |
+
],
|
239 |
+
[
|
240 |
+
672,
|
241 |
+
3024
|
242 |
+
],
|
243 |
+
[
|
244 |
+
672,
|
245 |
+
3360
|
246 |
+
],
|
247 |
+
[
|
248 |
+
672,
|
249 |
+
3696
|
250 |
+
],
|
251 |
+
[
|
252 |
+
672,
|
253 |
+
4032
|
254 |
+
],
|
255 |
+
[
|
256 |
+
672,
|
257 |
+
4368
|
258 |
+
],
|
259 |
+
[
|
260 |
+
672,
|
261 |
+
4704
|
262 |
+
],
|
263 |
+
[
|
264 |
+
672,
|
265 |
+
5040
|
266 |
+
],
|
267 |
+
[
|
268 |
+
672,
|
269 |
+
5376
|
270 |
+
],
|
271 |
+
[
|
272 |
+
672,
|
273 |
+
5712
|
274 |
+
],
|
275 |
+
[
|
276 |
+
672,
|
277 |
+
6048
|
278 |
+
],
|
279 |
+
[
|
280 |
+
672,
|
281 |
+
6384
|
282 |
+
],
|
283 |
+
[
|
284 |
+
672,
|
285 |
+
6720
|
286 |
+
],
|
287 |
+
[
|
288 |
+
672,
|
289 |
+
7056
|
290 |
+
],
|
291 |
+
[
|
292 |
+
672,
|
293 |
+
7392
|
294 |
+
],
|
295 |
+
[
|
296 |
+
672,
|
297 |
+
7728
|
298 |
+
],
|
299 |
+
[
|
300 |
+
672,
|
301 |
+
8064
|
302 |
+
],
|
303 |
+
[
|
304 |
+
1008,
|
305 |
+
336
|
306 |
+
],
|
307 |
+
[
|
308 |
+
1008,
|
309 |
+
672
|
310 |
+
],
|
311 |
+
[
|
312 |
+
1008,
|
313 |
+
1008
|
314 |
+
],
|
315 |
+
[
|
316 |
+
1008,
|
317 |
+
1344
|
318 |
+
],
|
319 |
+
[
|
320 |
+
1008,
|
321 |
+
1680
|
322 |
+
],
|
323 |
+
[
|
324 |
+
1008,
|
325 |
+
2016
|
326 |
+
],
|
327 |
+
[
|
328 |
+
1008,
|
329 |
+
2352
|
330 |
+
],
|
331 |
+
[
|
332 |
+
1008,
|
333 |
+
2688
|
334 |
+
],
|
335 |
+
[
|
336 |
+
1008,
|
337 |
+
3024
|
338 |
+
],
|
339 |
+
[
|
340 |
+
1008,
|
341 |
+
3360
|
342 |
+
],
|
343 |
+
[
|
344 |
+
1008,
|
345 |
+
3696
|
346 |
+
],
|
347 |
+
[
|
348 |
+
1008,
|
349 |
+
4032
|
350 |
+
],
|
351 |
+
[
|
352 |
+
1008,
|
353 |
+
4368
|
354 |
+
],
|
355 |
+
[
|
356 |
+
1008,
|
357 |
+
4704
|
358 |
+
],
|
359 |
+
[
|
360 |
+
1008,
|
361 |
+
5040
|
362 |
+
],
|
363 |
+
[
|
364 |
+
1008,
|
365 |
+
5376
|
366 |
+
],
|
367 |
+
[
|
368 |
+
1344,
|
369 |
+
336
|
370 |
+
],
|
371 |
+
[
|
372 |
+
1344,
|
373 |
+
672
|
374 |
+
],
|
375 |
+
[
|
376 |
+
1344,
|
377 |
+
1008
|
378 |
+
],
|
379 |
+
[
|
380 |
+
1344,
|
381 |
+
1344
|
382 |
+
],
|
383 |
+
[
|
384 |
+
1344,
|
385 |
+
1680
|
386 |
+
],
|
387 |
+
[
|
388 |
+
1344,
|
389 |
+
2016
|
390 |
+
],
|
391 |
+
[
|
392 |
+
1344,
|
393 |
+
2352
|
394 |
+
],
|
395 |
+
[
|
396 |
+
1344,
|
397 |
+
2688
|
398 |
+
],
|
399 |
+
[
|
400 |
+
1344,
|
401 |
+
3024
|
402 |
+
],
|
403 |
+
[
|
404 |
+
1344,
|
405 |
+
3360
|
406 |
+
],
|
407 |
+
[
|
408 |
+
1344,
|
409 |
+
3696
|
410 |
+
],
|
411 |
+
[
|
412 |
+
1344,
|
413 |
+
4032
|
414 |
+
],
|
415 |
+
[
|
416 |
+
1680,
|
417 |
+
336
|
418 |
+
],
|
419 |
+
[
|
420 |
+
1680,
|
421 |
+
672
|
422 |
+
],
|
423 |
+
[
|
424 |
+
1680,
|
425 |
+
1008
|
426 |
+
],
|
427 |
+
[
|
428 |
+
1680,
|
429 |
+
1344
|
430 |
+
],
|
431 |
+
[
|
432 |
+
1680,
|
433 |
+
1680
|
434 |
+
],
|
435 |
+
[
|
436 |
+
1680,
|
437 |
+
2016
|
438 |
+
],
|
439 |
+
[
|
440 |
+
1680,
|
441 |
+
2352
|
442 |
+
],
|
443 |
+
[
|
444 |
+
1680,
|
445 |
+
2688
|
446 |
+
],
|
447 |
+
[
|
448 |
+
1680,
|
449 |
+
3024
|
450 |
+
],
|
451 |
+
[
|
452 |
+
2016,
|
453 |
+
336
|
454 |
+
],
|
455 |
+
[
|
456 |
+
2016,
|
457 |
+
672
|
458 |
+
],
|
459 |
+
[
|
460 |
+
2016,
|
461 |
+
1008
|
462 |
+
],
|
463 |
+
[
|
464 |
+
2016,
|
465 |
+
1344
|
466 |
+
],
|
467 |
+
[
|
468 |
+
2016,
|
469 |
+
1680
|
470 |
+
],
|
471 |
+
[
|
472 |
+
2016,
|
473 |
+
2016
|
474 |
+
],
|
475 |
+
[
|
476 |
+
2016,
|
477 |
+
2352
|
478 |
+
],
|
479 |
+
[
|
480 |
+
2016,
|
481 |
+
2688
|
482 |
+
],
|
483 |
+
[
|
484 |
+
2352,
|
485 |
+
336
|
486 |
+
],
|
487 |
+
[
|
488 |
+
2352,
|
489 |
+
672
|
490 |
+
],
|
491 |
+
[
|
492 |
+
2352,
|
493 |
+
1008
|
494 |
+
],
|
495 |
+
[
|
496 |
+
2352,
|
497 |
+
1344
|
498 |
+
],
|
499 |
+
[
|
500 |
+
2352,
|
501 |
+
1680
|
502 |
+
],
|
503 |
+
[
|
504 |
+
2352,
|
505 |
+
2016
|
506 |
+
],
|
507 |
+
[
|
508 |
+
2352,
|
509 |
+
2352
|
510 |
+
],
|
511 |
+
[
|
512 |
+
2688,
|
513 |
+
336
|
514 |
+
],
|
515 |
+
[
|
516 |
+
2688,
|
517 |
+
672
|
518 |
+
],
|
519 |
+
[
|
520 |
+
2688,
|
521 |
+
1008
|
522 |
+
],
|
523 |
+
[
|
524 |
+
2688,
|
525 |
+
1344
|
526 |
+
],
|
527 |
+
[
|
528 |
+
2688,
|
529 |
+
1680
|
530 |
+
],
|
531 |
+
[
|
532 |
+
2688,
|
533 |
+
2016
|
534 |
+
],
|
535 |
+
[
|
536 |
+
3024,
|
537 |
+
336
|
538 |
+
],
|
539 |
+
[
|
540 |
+
3024,
|
541 |
+
672
|
542 |
+
],
|
543 |
+
[
|
544 |
+
3024,
|
545 |
+
1008
|
546 |
+
],
|
547 |
+
[
|
548 |
+
3024,
|
549 |
+
1344
|
550 |
+
],
|
551 |
+
[
|
552 |
+
3024,
|
553 |
+
1680
|
554 |
+
],
|
555 |
+
[
|
556 |
+
3360,
|
557 |
+
336
|
558 |
+
],
|
559 |
+
[
|
560 |
+
3360,
|
561 |
+
672
|
562 |
+
],
|
563 |
+
[
|
564 |
+
3360,
|
565 |
+
1008
|
566 |
+
],
|
567 |
+
[
|
568 |
+
3360,
|
569 |
+
1344
|
570 |
+
],
|
571 |
+
[
|
572 |
+
3696,
|
573 |
+
336
|
574 |
+
],
|
575 |
+
[
|
576 |
+
3696,
|
577 |
+
672
|
578 |
+
],
|
579 |
+
[
|
580 |
+
3696,
|
581 |
+
1008
|
582 |
+
],
|
583 |
+
[
|
584 |
+
3696,
|
585 |
+
1344
|
586 |
+
],
|
587 |
+
[
|
588 |
+
4032,
|
589 |
+
336
|
590 |
+
],
|
591 |
+
[
|
592 |
+
4032,
|
593 |
+
672
|
594 |
+
],
|
595 |
+
[
|
596 |
+
4032,
|
597 |
+
1008
|
598 |
+
],
|
599 |
+
[
|
600 |
+
4032,
|
601 |
+
1344
|
602 |
+
],
|
603 |
+
[
|
604 |
+
4368,
|
605 |
+
336
|
606 |
+
],
|
607 |
+
[
|
608 |
+
4368,
|
609 |
+
672
|
610 |
+
],
|
611 |
+
[
|
612 |
+
4368,
|
613 |
+
1008
|
614 |
+
],
|
615 |
+
[
|
616 |
+
4704,
|
617 |
+
336
|
618 |
+
],
|
619 |
+
[
|
620 |
+
4704,
|
621 |
+
672
|
622 |
+
],
|
623 |
+
[
|
624 |
+
4704,
|
625 |
+
1008
|
626 |
+
],
|
627 |
+
[
|
628 |
+
5040,
|
629 |
+
336
|
630 |
+
],
|
631 |
+
[
|
632 |
+
5040,
|
633 |
+
672
|
634 |
+
],
|
635 |
+
[
|
636 |
+
5040,
|
637 |
+
1008
|
638 |
+
],
|
639 |
+
[
|
640 |
+
5376,
|
641 |
+
336
|
642 |
+
],
|
643 |
+
[
|
644 |
+
5376,
|
645 |
+
672
|
646 |
+
],
|
647 |
+
[
|
648 |
+
5376,
|
649 |
+
1008
|
650 |
+
],
|
651 |
+
[
|
652 |
+
5712,
|
653 |
+
336
|
654 |
+
],
|
655 |
+
[
|
656 |
+
5712,
|
657 |
+
672
|
658 |
+
],
|
659 |
+
[
|
660 |
+
6048,
|
661 |
+
336
|
662 |
+
],
|
663 |
+
[
|
664 |
+
6048,
|
665 |
+
672
|
666 |
+
],
|
667 |
+
[
|
668 |
+
6384,
|
669 |
+
336
|
670 |
+
],
|
671 |
+
[
|
672 |
+
6384,
|
673 |
+
672
|
674 |
+
],
|
675 |
+
[
|
676 |
+
6720,
|
677 |
+
336
|
678 |
+
],
|
679 |
+
[
|
680 |
+
6720,
|
681 |
+
672
|
682 |
+
],
|
683 |
+
[
|
684 |
+
7056,
|
685 |
+
336
|
686 |
+
],
|
687 |
+
[
|
688 |
+
7056,
|
689 |
+
672
|
690 |
+
],
|
691 |
+
[
|
692 |
+
7392,
|
693 |
+
336
|
694 |
+
],
|
695 |
+
[
|
696 |
+
7392,
|
697 |
+
672
|
698 |
+
],
|
699 |
+
[
|
700 |
+
7728,
|
701 |
+
336
|
702 |
+
],
|
703 |
+
[
|
704 |
+
7728,
|
705 |
+
672
|
706 |
+
],
|
707 |
+
[
|
708 |
+
8064,
|
709 |
+
336
|
710 |
+
],
|
711 |
+
[
|
712 |
+
8064,
|
713 |
+
672
|
714 |
+
],
|
715 |
+
[
|
716 |
+
8400,
|
717 |
+
336
|
718 |
+
],
|
719 |
+
[
|
720 |
+
8736,
|
721 |
+
336
|
722 |
+
],
|
723 |
+
[
|
724 |
+
9072,
|
725 |
+
336
|
726 |
+
],
|
727 |
+
[
|
728 |
+
9408,
|
729 |
+
336
|
730 |
+
],
|
731 |
+
[
|
732 |
+
9744,
|
733 |
+
336
|
734 |
+
],
|
735 |
+
[
|
736 |
+
10080,
|
737 |
+
336
|
738 |
+
],
|
739 |
+
[
|
740 |
+
10416,
|
741 |
+
336
|
742 |
+
],
|
743 |
+
[
|
744 |
+
10752,
|
745 |
+
336
|
746 |
+
],
|
747 |
+
[
|
748 |
+
11088,
|
749 |
+
336
|
750 |
+
],
|
751 |
+
[
|
752 |
+
11424,
|
753 |
+
336
|
754 |
+
],
|
755 |
+
[
|
756 |
+
11760,
|
757 |
+
336
|
758 |
+
],
|
759 |
+
[
|
760 |
+
12096,
|
761 |
+
336
|
762 |
+
],
|
763 |
+
[
|
764 |
+
12432,
|
765 |
+
336
|
766 |
+
],
|
767 |
+
[
|
768 |
+
12768,
|
769 |
+
336
|
770 |
+
],
|
771 |
+
[
|
772 |
+
13104,
|
773 |
+
336
|
774 |
+
],
|
775 |
+
[
|
776 |
+
13440,
|
777 |
+
336
|
778 |
+
],
|
779 |
+
[
|
780 |
+
13776,
|
781 |
+
336
|
782 |
+
],
|
783 |
+
[
|
784 |
+
14112,
|
785 |
+
336
|
786 |
+
],
|
787 |
+
[
|
788 |
+
14448,
|
789 |
+
336
|
790 |
+
],
|
791 |
+
[
|
792 |
+
14784,
|
793 |
+
336
|
794 |
+
],
|
795 |
+
[
|
796 |
+
15120,
|
797 |
+
336
|
798 |
+
],
|
799 |
+
[
|
800 |
+
15456,
|
801 |
+
336
|
802 |
+
],
|
803 |
+
[
|
804 |
+
15792,
|
805 |
+
336
|
806 |
+
],
|
807 |
+
[
|
808 |
+
16128,
|
809 |
+
336
|
810 |
+
]
|
811 |
+
],
|
812 |
+
"initializer_range": 0.1,
|
813 |
+
"intermediate_size": 8192,
|
814 |
+
"layer_norm_epsilon": 1e-05,
|
815 |
+
"max_position_embeddings": 1000000000000000019884624838656,
|
816 |
+
"mm_hidden_size": 1024,
|
817 |
+
"mm_patch_merge_type": "spatial_unpad",
|
818 |
+
"mm_projector_lr": 2e-05,
|
819 |
+
"mm_projector_type": "linear",
|
820 |
+
"mm_use_im_patch_token": false,
|
821 |
+
"mm_use_im_start_end": false,
|
822 |
+
"mm_vision_select_feature": "patch",
|
823 |
+
"mm_vision_select_layer": -2,
|
824 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
825 |
+
"mm_vision_tower_lr": 2e-06,
|
826 |
+
"model_type": "falcon_mamba",
|
827 |
+
"num_hidden_layers": 64,
|
828 |
+
"pad_token_id": 0,
|
829 |
+
"rescale_prenorm_residual": false,
|
830 |
+
"residual_in_fp32": true,
|
831 |
+
"state_size": 16,
|
832 |
+
"tie_word_embeddings": false,
|
833 |
+
"time_step_floor": 0.0001,
|
834 |
+
"time_step_init_scheme": "random",
|
835 |
+
"time_step_max": 0.1,
|
836 |
+
"time_step_min": 0.001,
|
837 |
+
"time_step_rank": 256,
|
838 |
+
"time_step_scale": 1.0,
|
839 |
+
"tokenizer_model_max_length": 32896,
|
840 |
+
"tokenizer_padding_side": "right",
|
841 |
+
"torch_dtype": "bfloat16",
|
842 |
+
"transformers_version": "4.45.0.dev0",
|
843 |
+
"tune_mm_mlp_adapter": false,
|
844 |
+
"unfreeze_mm_vision_tower": true,
|
845 |
+
"use_bias": false,
|
846 |
+
"use_cache": false,
|
847 |
+
"use_conv_bias": true,
|
848 |
+
"use_mambapy": false,
|
849 |
+
"use_mm_proj": true,
|
850 |
+
"vocab_size": 65024
|
851 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3aaccec1a74afadb5d6ff20f9058f8d3e51de57a15e2e6c1ec0eafc120288944
|
3 |
+
size 4956192312
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa82bbf5611a20f5730d1e98b96f4a7617b12db2de2aa5f4aedfe6e487fdeaef
|
3 |
+
size 4987536920
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c917ebf03079fea8ff87d8d5fbfdde01f12957f4df5ddf55c1328785f2c3cc33
|
3 |
+
size 4684478664
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10fdf037b3f4a45376b1dc85840b448ef433ad6cfa3a01da1acf1f60e4a2bf14
|
3 |
+
size 532676736
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
">>TITLE<<",
|
4 |
+
">>ABSTRACT<<",
|
5 |
+
">>INTRODUCTION<<",
|
6 |
+
">>SUMMARY<<",
|
7 |
+
">>COMMENT<<",
|
8 |
+
">>ANSWER<<",
|
9 |
+
">>QUESTION<<",
|
10 |
+
"assistant",
|
11 |
+
"<|begin_of_text|>",
|
12 |
+
"<|im_start|>",
|
13 |
+
"<|im_end|>"
|
14 |
+
],
|
15 |
+
"bos_token": {
|
16 |
+
"content": "<|begin_of_text|>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"eos_token": {
|
23 |
+
"content": "<|end_of_text|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"pad_token": {
|
30 |
+
"content": ">>TITLE<<",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
}
|
36 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": ">>TITLE<<",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": ">>ABSTRACT<<",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": ">>INTRODUCTION<<",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": ">>SUMMARY<<",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": ">>COMMENT<<",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"5": {
|
45 |
+
"content": ">>ANSWER<<",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"6": {
|
53 |
+
"content": ">>QUESTION<<",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"7": {
|
61 |
+
"content": "assistant",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"8": {
|
69 |
+
"content": "<|begin_of_text|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"9": {
|
77 |
+
"content": "<|im_start|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"10": {
|
85 |
+
"content": "<|im_end|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"11": {
|
93 |
+
"content": "<|end_of_text|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
}
|
100 |
+
},
|
101 |
+
"additional_special_tokens": [
|
102 |
+
">>TITLE<<",
|
103 |
+
">>ABSTRACT<<",
|
104 |
+
">>INTRODUCTION<<",
|
105 |
+
">>SUMMARY<<",
|
106 |
+
">>COMMENT<<",
|
107 |
+
">>ANSWER<<",
|
108 |
+
">>QUESTION<<",
|
109 |
+
"assistant",
|
110 |
+
"<|begin_of_text|>",
|
111 |
+
"<|im_start|>",
|
112 |
+
"<|im_end|>"
|
113 |
+
],
|
114 |
+
"bos_token": "<|begin_of_text|>",
|
115 |
+
"chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
116 |
+
"clean_up_tokenization_spaces": true,
|
117 |
+
"eos_token": "<|end_of_text|>",
|
118 |
+
"max_length": null,
|
119 |
+
"model_input_names": [
|
120 |
+
"input_ids",
|
121 |
+
"attention_mask"
|
122 |
+
],
|
123 |
+
"model_max_length": 32896,
|
124 |
+
"pad_to_multiple_of": null,
|
125 |
+
"pad_token": ">>TITLE<<",
|
126 |
+
"pad_token_type_id": 0,
|
127 |
+
"padding_side": "right",
|
128 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
129 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71f3aa1a7744f55e0b995c5d995d21c3cbe39820b9d533547b6672503f8e2b9c
|
3 |
+
size 7544
|