Vaibhav Adlakha

@a-green-hand-jack Can you try to run [Instructor XL](https://huggingface.co/hkunlp/instructor-xl). It is a sentence-transformers model similar in size to Sheared Llama so it will be a more suitable comparison.

Closing as it is stale. @a-green-hand-jack - Feel free to re-open if you still need help on this.

Llama-3 has been added to the [model list](https://github.com/McGill-NLP/llm2vec?tab=readme-ov-file#model-list)

Fixed, thanks!

We did. [Here](https://x.com/vaibhav_adlakha/status/1785406274273751315?s=46&t=U0ISFfo1VSM4DDGABmLQjg) is a twitter/X thread summarizing our findings. All MTEB scores are also present in our Huggingface repo of these models. The results should be updated on the...

> @vaibhavad I have prepared an llm2vec version for Qwen2 but there are some problems, I wonder if you can give me the process to prepare code for a new...

@Iambestfeed It looks like your implementation is similar to Llama, however, looking to [modeling_qwen2.py](https://github.com/huggingface/transformers/blob/v4.40.1/src/transformers/models/qwen2/modeling_qwen2.py#L912) at transformers library, it seems the implementation is similar to Mistral. Different models differ on how...

Closing as it is stale. Feel free to re-open if there are any additional questions related to this issue

Yes it is definitely possible, all that will be required is to change the model name and the batch size in the [config](https://github.com/McGill-NLP/llm2vec/blob/main/train_configs/mntp/Llama2.json). For example, for Llama 13B, you should...

Feel free to re-open if you have any more questions about this issue.