mistralai
/

Mistral-Small-4-119B-2603

Model card Files Files and versions

Resources

View closed (8)

Anyone running this on 2×H200 with vLLM? Hangs after "Fp8 MoE backend"

#23 opened 2 months ago by

[Feature request] Eliminate pre-attention RMSNorm in Mistral-Small 4 via scale invariance + weight folding

#20 opened 4 months ago by

abc

#19 opened 5 months ago by

Create Dockerfile

#18 opened 5 months ago by

When using in vibe or opencode, often responds with just "Task completed" instead of actually doing the task

#16 opened 5 months ago by

Love the license, confused by some of the decisions.

#15 opened 5 months ago by

Wrong context length in context?

#14 opened 5 months ago by

Small?

#12 opened 5 months ago by

Please state benchmark versions

#11 opened 5 months ago by

harveensingh-sarvam

please make a 15B and 40B creative writting model. ❤️❤️

#6 opened 5 months ago by

UniversalLove333

"Small" model is now 120B and beyond the reach of most people, even in the upper-middle class with multiple consumer GPUs

#5 opened 5 months ago by

Recommended sampler?

#4 opened 5 months ago by

Video of Step-by-Step Review and Testing

#3 opened 5 months ago by

Add evaluation results

#2 opened 5 months ago by

French Hegemonia

#1 opened 5 months ago by