cannot understand using Meta-Llama-3-8B-Instruct as base model
#13 opened about 9 hours ago
by
dreaming12580
Expects to support inputs via inputs_embeds as inputs
#12 opened 1 day ago
by
vonchenplus
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1675930600450-62136d87cf7928035e81348e.jpeg)
CogVLM models are supported by LMDeploy for inference
#11 opened 22 days ago
by
RunningLeon
Is it possible that the owner or someone help to create the gguf files?
#9 opened about 2 months ago
by
Mikesssss
multiple image support?
5
#7 opened about 2 months ago
by
wamozart
output Discrepancy between Demo and Local
#6 opened about 2 months ago
by
yassin-eb
cannot be used on Apple MPS
2
#5 opened 2 months ago
by
ptx0
![](https://cdn-avatars.huggingface.co/v1/production/uploads/641caf6c043963b1c0a27256/CD7ktICDsldVJlpiND5kl.png)
Does the visual model freeze during the pre training phase
2
#4 opened 2 months ago
by
paul91
Quantizing the model - on our own
4
#3 opened 2 months ago
by
christianweyer
![](https://cdn-avatars.huggingface.co/v1/production/uploads/644cf21fd1945fe77a13df6a/7rxLPqRgHi6POSs0DR3A0.png)
Device_map Auto fails
6
#2 opened 2 months ago
by
arnaudstiegler
Demo for the model
5
#1 opened 2 months ago
by
mervenoyan
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1613845120202-noauth.png)