Edouard Balzin's picture

9

Edouard Balzin

nfunctor

·

AI & ML interests

None yet

Recent Activity

new activity 13 days ago

ISTA-DASLab/Mistral-Small-3.1-24B-Instruct-2503-GPTQ-4b-128g:VLLM launch command?

new activity 2 months ago

deepseek-ai/DeepSeek-R1:R1 distill to Mistral Small?

new activity 2 months ago

casperhansen/mistral-small-24b-instruct-2501-awq:Comparison to older-type AWQ quants?

View all activity

Organizations

nfunctor's activity

New activity in ISTA-DASLab/Mistral-Small-3.1-24B-Instruct-2503-GPTQ-4b-128g 13 days ago

VLLM launch command?

#1 opened 13 days ago by

New activity in deepseek-ai/DeepSeek-R1 2 months ago

R1 distill to Mistral Small?

#99 opened 2 months ago by

New activity in casperhansen/mistral-small-24b-instruct-2501-awq 2 months ago

Comparison to older-type AWQ quants?

#1 opened 2 months ago by

New activity in casperhansen/deepseek-r1-distill-qwen-32b-awq 2 months ago

Generation configs: Unquantised vs AWQ, model weights format

#1 opened 2 months ago by

New activity in OpenGVLab/InternVL2_5-26B-AWQ 3 months ago

Model weights size clarification ?

#2 opened 3 months ago by

New activity in arcee-ai/SuperNova-Medius-FP8 5 months ago

Tokenizer update — needed or not?

#1 opened 5 months ago by

New activity in neuralmagic/Phi-3.5-mini-instruct-FP8-KV 6 months ago

latest vllm docker (v0.6.2) fail to load

#1 opened 6 months ago by

New activity in neuralmagic/README 7 months ago

Phi 3.5 MoE fp8 ?

#2 opened 7 months ago by

New activity in mlabonne/Daredevil-8B 9 months ago

Chat templates and "censored" performance

#3 opened 10 months ago by

Chat templates and "censored" performance

#3 opened 10 months ago by

New activity in mlabonne/Daredevil-8B 10 months ago

Chat templates and "censored" performance

#3 opened 10 months ago by