Instructions to use codefuse-ai/F2LLM-v2-160M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codefuse-ai/F2LLM-v2-160M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="codefuse-ai/F2LLM-v2-160M")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/F2LLM-v2-160M") model = AutoModel.from_pretrained("codefuse-ai/F2LLM-v2-160M", device_map="auto") - sentence-transformers
How to use codefuse-ai/F2LLM-v2-160M with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("codefuse-ai/F2LLM-v2-160M") 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] - Inference
- Notebooks
- Google Colab
- Kaggle
fix hidden size
#2
by BramVanroy - opened
AFAICT the hidden size of the model is 640 so the pooling dimension would also be 640 https://huggingface.co/codefuse-ai/F2LLM-v2-160M/blob/main/config.json#L12
Geralt-Targaryen changed pull request status to merged
Hi @Geralt-Targaryen , thanks for the merge! I'd really appreciate it if you could also merge the other PRs I made for all other F2LLM v2 models that have the same problem. We'd love to build on your models after this fix.