can this model run on cpu, I had a error when I test it on cpu, this with a error about should install flash_attn
#15 opened 7 months ago
by
wiseluke
Can this model be fine tuned?
2
#12 opened 7 months ago
by
rvsh
Comparison against Mistral's own release
#11 opened 7 months ago
by
migtissera
![](https://cdn-avatars.huggingface.co/v1/production/uploads/647a6317555b5e199cffd5a2/SE6vWIFxkQjAc_9BrG8Al.png)
no module named transformers.cache_utils
11
#9 opened 7 months ago
by
gpucce
![](https://cdn-avatars.huggingface.co/v1/production/uploads/60c72bad2c6fd4f486d25b4b/H-hZfI-td4Ngyn7rORyx2.jpeg)
Use with VLLM now
#6 opened 7 months ago
by
0-hero
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6382255fcae34727b9cc149e/PYiwi8LVZParYvImmcGez.png)
Update modeling_moe_mistral.py
#5 opened 7 months ago
by
bjoernp
Flash dependency (locks out non-NVIDIA GPUs)
3
#4 opened 7 months ago
by
Thalesian
Really appreciate the work put into this! I have noticed a change in the model output since first release.
2
#3 opened 7 months ago
by
AARon99
thank you!
3
#2 opened 8 months ago
by
perlthoughts
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6448573b30fa4ecb85e2d184/Rn2MWykBh5BfOEZ2z0Vgi.png)