Dragan Stoll's picture

2 2 2

Dragan Stoll

dragstoll

·

dragstoll

AI & ML interests

NLP, Prediction

Recent Activity

upvoted an article 19 days ago

Open-R1: a fully open reproduction of DeepSeek-R1

liked a model 7 months ago

unsloth/Mistral-Large-Instruct-2407-bnb-4bit

new activity 9 months ago

mistralai/Mixtral-8x22B-v0.1:Support for quantized cache

View all activity

Organizations

None yet

dragstoll's activity

New activity in mistralai/Mixtral-8x22B-v0.1 9 months ago

Support for quantized cache

#5 opened 9 months ago by

New activity in mistralai/Mixtral-8x7B-v0.1 about 1 year ago

AutoModelForCausalLM does not seem to work for Mixtral

#8 opened about 1 year ago by