Raushan Turganbay
RaushanTurganbay
AI & ML interests
Generation and Multimodality
Recent Activity
new activity
2 days ago
microsoft/Phi-4-multimodal-instruct:Convert to HF format
new activity
2 days ago
microsoft/Phi-4-multimodal-instruct:HF format chat template
updated
a dataset
4 days ago
RaushanTurganbay/OK-VQA-hw
Organizations
RaushanTurganbay's activity
Convert to HF format
2
#55 opened 3 days ago
by
cyrilvallez

HF format chat template
#56 opened 2 days ago
by
RaushanTurganbay
Cannot apply chat template from tokenizer
1
#31 opened 14 days ago
by
DarkLight1337
prefill assistant responses
1
#16 opened 23 days ago
by
alexsafayan

Can't reproduce given example (no meaningful output)
1
#8 opened 24 days ago
by
pzarzycki

Change chat template into the one for mistralai/Mistral-7B-Instruct-v0.2
1
#3 opened about 1 month ago
by
ruiqiRichard
Is this a working model?
4
#2 opened about 1 month ago
by
ruiqiRichard
Update processor_config.json
1
#1 opened about 1 month ago
by
RaushanTurganbay
Support of flash attention 2?
2
#29 opened about 2 months ago
by
LuciusLan
Fix typo in chat template (assistant EOS token)
#43 opened about 2 months ago
by
fabric
<\s> token in the chat template instead of the </s> EOS token
4
#41 opened 3 months ago
by
fabric
Incorrect Weights in Model Repositories
3
#2 opened about 2 months ago
by
francescortu

Getting shape mismatch while loading saved Pixtral model
4
#24 opened about 2 months ago
by
ss007
Update README.md
#3 opened about 2 months ago
by
RaushanTurganbay
AttributeError: 'CLIPImageProcessor' object has no attribute 'patch_size' when loading fine-tuned LLaVA model from Google Drive
2
#47 opened about 2 months ago
by
mdnasif
Update README with new chat template example
1
#18 opened about 2 months ago
by
RaushanTurganbay
Is the chat template correct? (issue for vLLM)
7
#22 opened 3 months ago
by
MichaelAI23
TypeError: LlavaNextProcessor.__init__() got an unexpected keyword argument 'image_token'
1
#10 opened 2 months ago
by
JBod
