How to use BillSYZhang/gte-Qwen2-7B-instruct-Q4-mlx with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("BillSYZhang/gte-Qwen2-7B-instruct-Q4-mlx", trust_remote_code=True) 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]
How to use BillSYZhang/gte-Qwen2-7B-instruct-Q4-mlx with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BillSYZhang/gte-Qwen2-7B-instruct-Q4-mlx", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("BillSYZhang/gte-Qwen2-7B-instruct-Q4-mlx", trust_remote_code=True)
How to use BillSYZhang/gte-Qwen2-7B-instruct-Q4-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gte-Qwen2-7B-instruct-Q4-mlx BillSYZhang/gte-Qwen2-7B-instruct-Q4-mlx
gregbarbosa