Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
3
1
2
Rayen
Lissanro
Follow
https://Dragon.Studio
Lissanro
AI & ML interests
None yet
Organizations
None yet
Lissanro
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
New activity in
turboderp/Llama-3-70B-Instruct-exl2
6 months ago
tokenizer_config.json and config.json specify wrong EOS token, causing the model to not function correctly in backends which do not read EOS tokens from generation_config.json
6
#1 opened 6 months ago by
Lissanro
New activity in
LoneStriker/Meta-Llama-3-8B-Instruct-8.0bpw-h8-exl2
6 months ago
Works great on oobabooga, but always ends with assistant
1
#3 opened 6 months ago by
Noodlz
New activity in
alpindale/WizardLM-2-8x22B
6 months ago
This could likely be dewokefied and possible even improved using mergekit's new 'Model Stock' method!
31
#5 opened 6 months ago by
jukofyork