Add new SentenceTransformer model.
Browse files- README.md +148 -95
- config.json +1 -1
- model.safetensors +1 -1
README.md
CHANGED
@@ -9,31 +9,31 @@ tags:
|
|
9 |
- loss:CachedGISTEmbedLoss
|
10 |
base_model: nomic-ai/nomic-embed-text-v1.5
|
11 |
widget:
|
12 |
-
- source_sentence: 'search_query:
|
13 |
sentences:
|
14 |
-
- 'search_query:
|
15 |
-
- 'search_query:
|
16 |
-
- 'search_query:
|
17 |
-
- source_sentence: 'search_query:
|
18 |
sentences:
|
19 |
-
- 'search_query:
|
20 |
-
- 'search_query:
|
21 |
-
- 'search_query:
|
22 |
-
- source_sentence: 'search_query:
|
23 |
sentences:
|
24 |
-
- 'search_query:
|
25 |
-
- 'search_query:
|
26 |
-
- 'search_query:
|
27 |
-
- source_sentence: 'search_query:
|
28 |
sentences:
|
29 |
-
- 'search_query:
|
30 |
-
- 'search_query:
|
31 |
-
- 'search_query:
|
32 |
-
- source_sentence: 'search_query:
|
33 |
sentences:
|
34 |
-
- 'search_query:
|
35 |
-
- 'search_query:
|
36 |
-
- 'search_query:
|
37 |
pipeline_tag: sentence-similarity
|
38 |
---
|
39 |
|
@@ -86,9 +86,9 @@ from sentence_transformers import SentenceTransformer
|
|
86 |
model = SentenceTransformer("sentence_transformers_model_id")
|
87 |
# Run inference
|
88 |
sentences = [
|
89 |
-
'search_query:
|
90 |
-
'search_query:
|
91 |
-
'search_query:
|
92 |
]
|
93 |
embeddings = model.encode(sentences)
|
94 |
print(embeddings.shape)
|
@@ -286,79 +286,132 @@ You can finetune this model on your own dataset.
|
|
286 |
</details>
|
287 |
|
288 |
### Training Logs
|
289 |
-
|
290 |
-
|
291 |
-
|
|
292 |
-
|
293 |
-
| 0.
|
294 |
-
| 0.
|
295 |
-
| 0.
|
296 |
-
| 0.
|
297 |
-
| 0.
|
298 |
-
| 0.
|
299 |
-
| 0.
|
300 |
-
| 0.
|
301 |
-
| 0.
|
302 |
-
| 0.
|
303 |
-
| 0.
|
304 |
-
| 0.
|
305 |
-
| 0.
|
306 |
-
| 0.
|
307 |
-
| 0.
|
308 |
-
| 0.
|
309 |
-
| 0.
|
310 |
-
| 0.
|
311 |
-
| 0.
|
312 |
-
| 0.
|
313 |
-
| 0.
|
314 |
-
| 0.
|
315 |
-
| 0.
|
316 |
-
| 0.
|
317 |
-
| 0.
|
318 |
-
| 0.
|
319 |
-
| 0.
|
320 |
-
| 0.
|
321 |
-
| 0.
|
322 |
-
| 0.
|
323 |
-
| 0.
|
324 |
-
| 0.
|
325 |
-
| 0.
|
326 |
-
| 0.
|
327 |
-
| 0.
|
328 |
-
| 0.
|
329 |
-
| 0.
|
330 |
-
| 0.
|
331 |
-
| 0.
|
332 |
-
| 0.
|
333 |
-
| 0.
|
334 |
-
| 0.
|
335 |
-
| 0.
|
336 |
-
| 0.
|
337 |
-
| 0.
|
338 |
-
| 0.
|
339 |
-
| 0.
|
340 |
-
| 0.
|
341 |
-
| 0.
|
342 |
-
| 0.
|
343 |
-
| 0.
|
344 |
-
| 0.
|
345 |
-
| 0.
|
346 |
-
| 0.
|
347 |
-
| 0.
|
348 |
-
| 0.
|
349 |
-
| 0.
|
350 |
-
| 0.
|
351 |
-
| 0.
|
352 |
-
| 0.
|
353 |
-
| 0.
|
354 |
-
| 0.
|
355 |
-
| 0.
|
356 |
-
| 0.
|
357 |
-
| 0.
|
358 |
-
| 0.
|
359 |
-
| 0.
|
360 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
361 |
|
|
|
362 |
|
363 |
### Framework Versions
|
364 |
- Python: 3.10.12
|
|
|
9 |
- loss:CachedGISTEmbedLoss
|
10 |
base_model: nomic-ai/nomic-embed-text-v1.5
|
11 |
widget:
|
12 |
+
- source_sentence: 'search_query: ipad'
|
13 |
sentences:
|
14 |
+
- 'search_query: ipad newest model'
|
15 |
+
- 'search_query: epyc amd cpu'
|
16 |
+
- 'search_query: 35x29 mens jeans'
|
17 |
+
- source_sentence: 'search_query: 掲示板'
|
18 |
sentences:
|
19 |
+
- 'search_query: 寝袋 冬'
|
20 |
+
- 'search_query: lg ゲーミングモニター'
|
21 |
+
- 'search_query: vga to dvi-d'
|
22 |
+
- source_sentence: 'search_query: ダイアン'
|
23 |
sentences:
|
24 |
+
- 'search_query: ゴアテックス レインウェア'
|
25 |
+
- 'search_query: roy vickery'
|
26 |
+
- 'search_query: cbd oil not hemp'
|
27 |
+
- source_sentence: 'search_query: psp'
|
28 |
sentences:
|
29 |
+
- 'search_query: petechtool'
|
30 |
+
- 'search_query: heavy cream'
|
31 |
+
- 'search_query: sweaters for women'
|
32 |
+
- source_sentence: 'search_query: 龍師の翼'
|
33 |
sentences:
|
34 |
+
- 'search_query: 烏龍茶 2l'
|
35 |
+
- 'search_query: 筆箱プラスチックケース'
|
36 |
+
- 'search_query: fitbit for kids'
|
37 |
pipeline_tag: sentence-similarity
|
38 |
---
|
39 |
|
|
|
86 |
model = SentenceTransformer("sentence_transformers_model_id")
|
87 |
# Run inference
|
88 |
sentences = [
|
89 |
+
'search_query: 龍師の翼',
|
90 |
+
'search_query: 烏龍茶 2l',
|
91 |
+
'search_query: 筆箱プラスチックケース',
|
92 |
]
|
93 |
embeddings = model.encode(sentences)
|
94 |
print(embeddings.shape)
|
|
|
286 |
</details>
|
287 |
|
288 |
### Training Logs
|
289 |
+
<details><summary>Click to expand</summary>
|
290 |
+
|
291 |
+
| Epoch | Step | Training Loss |
|
292 |
+
|:------:|:-----:|:-------------:|
|
293 |
+
| 0.0009 | 100 | 3.7009 |
|
294 |
+
| 0.0018 | 200 | 3.3796 |
|
295 |
+
| 0.0027 | 300 | 2.8348 |
|
296 |
+
| 0.0036 | 400 | 2.1803 |
|
297 |
+
| 0.0045 | 500 | 1.8272 |
|
298 |
+
| 0.0054 | 600 | 1.4715 |
|
299 |
+
| 0.0063 | 700 | 1.0056 |
|
300 |
+
| 0.0072 | 800 | 0.7984 |
|
301 |
+
| 0.0081 | 900 | 0.6925 |
|
302 |
+
| 0.0091 | 1000 | 0.6552 |
|
303 |
+
| 0.0100 | 1100 | 0.6054 |
|
304 |
+
| 0.0109 | 1200 | 0.5874 |
|
305 |
+
| 0.0118 | 1300 | 0.5641 |
|
306 |
+
| 0.0127 | 1400 | 0.528 |
|
307 |
+
| 0.0136 | 1500 | 0.5285 |
|
308 |
+
| 0.0145 | 1600 | 0.5032 |
|
309 |
+
| 0.0154 | 1700 | 0.5238 |
|
310 |
+
| 0.0163 | 1800 | 0.4565 |
|
311 |
+
| 0.0172 | 1900 | 0.4739 |
|
312 |
+
| 0.0181 | 2000 | 0.4614 |
|
313 |
+
| 0.0190 | 2100 | 0.4334 |
|
314 |
+
| 0.0199 | 2200 | 0.4217 |
|
315 |
+
| 0.0208 | 2300 | 0.3931 |
|
316 |
+
| 0.0217 | 2400 | 0.4102 |
|
317 |
+
| 0.0226 | 2500 | 0.3936 |
|
318 |
+
| 0.0235 | 2600 | 0.415 |
|
319 |
+
| 0.0244 | 2700 | 0.4462 |
|
320 |
+
| 0.0253 | 2800 | 0.3886 |
|
321 |
+
| 0.0263 | 2900 | 0.3887 |
|
322 |
+
| 0.0272 | 3000 | 0.3629 |
|
323 |
+
| 0.0281 | 3100 | 0.37 |
|
324 |
+
| 0.0290 | 3200 | 0.3861 |
|
325 |
+
| 0.0299 | 3300 | 0.3813 |
|
326 |
+
| 0.0308 | 3400 | 0.3348 |
|
327 |
+
| 0.0317 | 3500 | 0.3566 |
|
328 |
+
| 0.0326 | 3600 | 0.3674 |
|
329 |
+
| 0.0335 | 3700 | 0.3421 |
|
330 |
+
| 0.0344 | 3800 | 0.3225 |
|
331 |
+
| 0.0353 | 3900 | 0.406 |
|
332 |
+
| 0.0362 | 4000 | 0.3975 |
|
333 |
+
| 0.0371 | 4100 | 0.368 |
|
334 |
+
| 0.0380 | 4200 | 0.3481 |
|
335 |
+
| 0.0389 | 4300 | 0.3405 |
|
336 |
+
| 0.0398 | 4400 | 0.3529 |
|
337 |
+
| 0.0407 | 4500 | 0.3968 |
|
338 |
+
| 0.0416 | 4600 | 0.3634 |
|
339 |
+
| 0.0425 | 4700 | 0.3518 |
|
340 |
+
| 0.0434 | 4800 | 0.383 |
|
341 |
+
| 0.0444 | 4900 | 0.3261 |
|
342 |
+
| 0.0453 | 5000 | 0.323 |
|
343 |
+
| 0.0462 | 5100 | 0.3372 |
|
344 |
+
| 0.0471 | 5200 | 0.358 |
|
345 |
+
| 0.0480 | 5300 | 0.3207 |
|
346 |
+
| 0.0489 | 5400 | 0.341 |
|
347 |
+
| 0.0498 | 5500 | 0.3146 |
|
348 |
+
| 0.0507 | 5600 | 0.3065 |
|
349 |
+
| 0.0516 | 5700 | 0.3597 |
|
350 |
+
| 0.0525 | 5800 | 0.3352 |
|
351 |
+
| 0.0534 | 5900 | 0.3212 |
|
352 |
+
| 0.0543 | 6000 | 0.316 |
|
353 |
+
| 0.0552 | 6100 | 0.3405 |
|
354 |
+
| 0.0561 | 6200 | 0.3416 |
|
355 |
+
| 0.0570 | 6300 | 0.3124 |
|
356 |
+
| 0.0579 | 6400 | 0.3146 |
|
357 |
+
| 0.0588 | 6500 | 0.3043 |
|
358 |
+
| 0.0597 | 6600 | 0.3687 |
|
359 |
+
| 0.0606 | 6700 | 0.3359 |
|
360 |
+
| 0.0616 | 6800 | 0.3414 |
|
361 |
+
| 0.0625 | 6900 | 0.3161 |
|
362 |
+
| 0.0634 | 7000 | 0.3266 |
|
363 |
+
| 0.0643 | 7100 | 0.3465 |
|
364 |
+
| 0.0652 | 7200 | 0.3017 |
|
365 |
+
| 0.0661 | 7300 | 0.33 |
|
366 |
+
| 0.0670 | 7400 | 0.3324 |
|
367 |
+
| 0.0679 | 7500 | 0.2829 |
|
368 |
+
| 0.0688 | 7600 | 0.2691 |
|
369 |
+
| 0.0697 | 7700 | 0.2939 |
|
370 |
+
| 0.0706 | 7800 | 0.2769 |
|
371 |
+
| 0.0715 | 7900 | 0.3092 |
|
372 |
+
| 0.0724 | 8000 | 0.2761 |
|
373 |
+
| 0.0733 | 8100 | 0.2858 |
|
374 |
+
| 0.0742 | 8200 | 0.3667 |
|
375 |
+
| 0.0751 | 8300 | 0.304 |
|
376 |
+
| 0.0760 | 8400 | 0.2971 |
|
377 |
+
| 0.0769 | 8500 | 0.3284 |
|
378 |
+
| 0.0778 | 8600 | 0.2915 |
|
379 |
+
| 0.0788 | 8700 | 0.2903 |
|
380 |
+
| 0.0797 | 8800 | 0.3132 |
|
381 |
+
| 0.0806 | 8900 | 0.2999 |
|
382 |
+
| 0.0815 | 9000 | 0.3191 |
|
383 |
+
| 0.0824 | 9100 | 0.2846 |
|
384 |
+
| 0.0833 | 9200 | 0.2966 |
|
385 |
+
| 0.0842 | 9300 | 0.3075 |
|
386 |
+
| 0.0851 | 9400 | 0.2814 |
|
387 |
+
| 0.0860 | 9500 | 0.3161 |
|
388 |
+
| 0.0869 | 9600 | 0.3056 |
|
389 |
+
| 0.0878 | 9700 | 0.2874 |
|
390 |
+
| 0.0887 | 9800 | 0.3238 |
|
391 |
+
| 0.0896 | 9900 | 0.3018 |
|
392 |
+
| 0.0905 | 10000 | 0.2994 |
|
393 |
+
| 0.0914 | 10100 | 0.2794 |
|
394 |
+
| 0.0923 | 10200 | 0.2581 |
|
395 |
+
| 0.0932 | 10300 | 0.3097 |
|
396 |
+
| 0.0941 | 10400 | 0.2711 |
|
397 |
+
| 0.0950 | 10500 | 0.2428 |
|
398 |
+
| 0.0960 | 10600 | 0.3025 |
|
399 |
+
| 0.0969 | 10700 | 0.3062 |
|
400 |
+
| 0.0978 | 10800 | 0.3189 |
|
401 |
+
| 0.0987 | 10900 | 0.3237 |
|
402 |
+
| 0.0996 | 11000 | 0.2843 |
|
403 |
+
| 0.1005 | 11100 | 0.2671 |
|
404 |
+
| 0.1014 | 11200 | 0.2939 |
|
405 |
+
| 0.1023 | 11300 | 0.2976 |
|
406 |
+
| 0.1032 | 11400 | 0.2991 |
|
407 |
+
| 0.1041 | 11500 | 0.2456 |
|
408 |
+
| 0.1050 | 11600 | 0.2895 |
|
409 |
+
| 0.1059 | 11700 | 0.2743 |
|
410 |
+
| 0.1068 | 11800 | 0.2827 |
|
411 |
+
| 0.1077 | 11900 | 0.3276 |
|
412 |
+
| 0.1086 | 12000 | 0.2813 |
|
413 |
|
414 |
+
</details>
|
415 |
|
416 |
### Framework Versions
|
417 |
- Python: 3.10.12
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "models/nomic-embed-text-esci/checkpoint-
|
3 |
"activation_function": "swiglu",
|
4 |
"architectures": [
|
5 |
"NomicBertModel"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "models/nomic-embed-text-esci/checkpoint-12000",
|
3 |
"activation_function": "swiglu",
|
4 |
"architectures": [
|
5 |
"NomicBertModel"
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 546938168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:500226d858088d74a7ddb26f1a85df2580931140b8f28fe5ef48cd46d768e58d
|
3 |
size 546938168
|