Instructions to use giangndm/F2LLM-v2-330M-model2vec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Model2Vec
How to use giangndm/F2LLM-v2-330M-model2vec with Model2Vec:
from model2vec import StaticModel model = StaticModel.from_pretrained("giangndm/F2LLM-v2-330M-model2vec") - sentence-transformers
How to use giangndm/F2LLM-v2-330M-model2vec with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("giangndm/F2LLM-v2-330M-model2vec") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_type": "model2vec", | |
| "architectures": [ | |
| "StaticModel" | |
| ], | |
| "tokenizer_name": "codefuse-ai/F2LLM-v2-330M", | |
| "apply_pca": 512, | |
| "sif_coefficient": 0.0001, | |
| "hidden_dim": 512, | |
| "seq_length": 1000000, | |
| "normalize": true, | |
| "pooling": "mean", | |
| "embedding_dtype": "float16" | |
| } |