Hugging Face's logo

DiscoResearch
/
mixtral-7b-8expert

Text Generation
Transformers
PyTorch
mistral
custom_code
text-generation-inference
Inference Endpoints
Model card Files Community
16

Can this model be fine tuned?

#12
by rvsh - opened
Discussion
rvsh

Can this model be fine tuned? For example with this dataset for polish language?
https://huggingface.co/datasets/mmosiolek/pl_alpaca_data_cleaned

myzz

3232

Cxxs

LLaMA2-Accessory now supports the inference and instruction finetuning (both full-parameter and PEFT like LoRA) of mixtral-8x7b-32kseqlen. It supports the load balancing loss and some other MoE support. The document is available here

Sign up or log in to comment