mistralai
/

Mistral-Small-3.1-24B-Instruct-2503

Model card Files Files and versions

Resources

View closed (21)

Mistral3ForConditionalGeneration has no vLLM implementation and the Transformers implementation is not compatible with vLLM. Try setting VLLM_USE_V1=0.

#16 opened 5 months ago by

set model_max_length to the maximum length of model context (131072 tokens)

#15 opened 5 months ago by

Problem with `mistral3` when loading the model

#14 opened 5 months ago by

Add chat_template to tokenizer_config.json

#11 opened 5 months ago by

本地部署+测评视频

#9 opened 5 months ago by

Can't wait for HF? try chatllm.cpp

#7 opened 5 months ago by

You did it again...

#4 opened 5 months ago by

HF Format?

#2 opened 5 months ago by