Instructions to use Muennighoff/SGPT-125M-mean-nli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Muennighoff/SGPT-125M-mean-nli with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Muennighoff/SGPT-125M-mean-nli") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use Muennighoff/SGPT-125M-mean-nli with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Muennighoff/SGPT-125M-mean-nli") model = AutoModel.from_pretrained("Muennighoff/SGPT-125M-mean-nli") - Notebooks
- Google Colab
- Kaggle
| epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman | |
| 0,880,0.7924220294328599,0.7995148933907719,0.7955983681180001,0.8005330478299068,0.7998619833498706,0.8049548668958452,0.617900992679522,0.6530310716601536 | |
| 0,1760,0.8134998996170658,0.824247518999946,0.8058060409576085,0.8128175983006478,0.8059488877633912,0.8139794460775402,0.6707714309358518,0.691993365452363 | |
| 0,2640,0.8226982197074469,0.8318282395339733,0.8098797337474397,0.8165527699174756,0.8095544136288466,0.8168884836722868,0.6874052388419072,0.7046431001607276 | |
| 0,3520,0.8237528925731339,0.8332057600575684,0.8122773391616722,0.81932616684922,0.8110044055831965,0.8191268375301659,0.6718989828728554,0.697059390300794 | |
| 0,4400,0.8252459359306298,0.8330376887672036,0.8079964420988573,0.8147308006885849,0.8050567266619668,0.8131677302148753,0.6824395058247997,0.7050888584754677 | |
| 0,5280,0.8239299547754487,0.8334258954408031,0.8059132100297753,0.8119085905558941,0.8043130674121882,0.8109660810086611,0.6732595594481693,0.7005318357576638 | |
| 0,6160,0.8247474446921976,0.8342096700030465,0.8035967898532747,0.8096956673205472,0.8012540501053195,0.8088275154758746,0.6816191515257244,0.7054614690528949 | |
| 0,7040,0.8301797180951206,0.8386010378022596,0.8061101176238306,0.8128188847784038,0.8032950020426607,0.8111166129723272,0.6914410502191741,0.7143848228210941 | |
| 0,7920,0.828140006692049,0.8368271024143468,0.8048296373114413,0.8116103163286995,0.8025575355349931,0.8103178688175507,0.6862216756260522,0.7104281415195944 | |
| 0,8800,0.8279713033379068,0.836644112818224,0.8043041804612308,0.8111949555531522,0.8018756352036762,0.8100206017084889,0.6870514058389051,0.7118055392673044 | |
| 0,-1,0.8279547129930442,0.8366443264874994,0.8042942804032979,0.8112074566200769,0.8018584637083337,0.8099924148562966,0.687019446039196,0.7117482830000332 | |