Sentence Similarity
sentence-transformers
Safetensors
Transformers
qwen2
text-generation
mteb
Qwen
custom_code
Eval Results (legacy)
text-embeddings-inference
Instructions to use Alibaba-NLP/gte-Qwen1.5-7B-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Alibaba-NLP/gte-Qwen1.5-7B-instruct with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Alibaba-NLP/gte-Qwen1.5-7B-instruct", 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] - Transformers
How to use Alibaba-NLP/gte-Qwen1.5-7B-instruct with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Alibaba-NLP/gte-Qwen1.5-7B-instruct", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Alibaba-NLP/gte-Qwen1.5-7B-instruct", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
how to finetune this model
#8
by enbacheng - opened
will you have a plan to release the pretrain and finetune script
We currently have no plans to open-source the pretrain and finetune script; our primary focus remains on releasing models with even better performance. Thank you for your interest in the GTE models.
So, are you saying that we cannot fine-tune the model using our own data source?
So, are you saying that we cannot fine-tune the model using our own data source?
You can refer to other open-source code like Gritlm[https://github.com/ContextualAI/gritlm/tree/main] and motify it to finetune the GTE model .