Raushan Turganbay
RaushanTurganbay
AI & ML interests
Generation and Multimodality
Recent Activity
updated
a model
about 9 hours ago
unsloth/llava-1.5-7b-hf-bnb-4bit
new activity
about 9 hours ago
unsloth/llava-1.5-7b-hf-bnb-4bit:Update processor_config.json
new activity
1 day ago
mistral-community/pixtral-12b:Support of flash attention 2?
Organizations
RaushanTurganbay's activity
Update processor_config.json
#1 opened about 9 hours ago
by
RaushanTurganbay
Support of flash attention 2?
2
#29 opened 1 day ago
by
LuciusLan
Fix typo in chat template (assistant EOS token)
#43 opened 4 days ago
by
fabric
<\s> token in the chat template instead of the </s> EOS token
4
#41 opened about 1 month ago
by
fabric
Incorrect Weights in Model Repositories
3
#2 opened 6 days ago
by
francescortu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1669983177160-noauth.jpeg)
Getting shape mismatch while loading saved Pixtral model
4
#24 opened 7 days ago
by
ss007
Update README.md
#3 opened 7 days ago
by
RaushanTurganbay
Update README with new chat template example
1
#18 opened 15 days ago
by
RaushanTurganbay
Is the chat template correct? (issue for vLLM)
7
#22 opened about 1 month ago
by
MichaelAI23
TypeError: LlavaNextProcessor.__init__() got an unexpected keyword argument 'image_token'
1
#10 opened 21 days ago
by
JBod
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/_7MLBjHUeLnD8GOgAUbov.png)
Store chat template in its own file
1
#13 opened 25 days ago
by
RaushanTurganbay
Update: convert weights again
1
#2 opened 28 days ago
by
RaushanTurganbay
Update README.md
#1 opened 29 days ago
by
RaushanTurganbay
Update README.md
#1 opened 29 days ago
by
RaushanTurganbay
Hello, can you support the conversion of llava to onnx
1
#22 opened 11 months ago
by
YinZiQi
Transformers update
1
#4 opened about 1 month ago
by
RaushanTurganbay
Transformers release
1
#6 opened about 1 month ago
by
RaushanTurganbay