Uday Pratap Singh Atwal
upsatwal
AI & ML interests
Inference optimization, ML Ops
Recent Activity
liked
a Space
29 days ago
yonigozlan/Transformers-Timeline
reacted
to
prithivMLmods's
post
with 🤗
about 2 months ago
Comparing: DeepCaption-VLA-7B, built on Qwen2.5-VL-7B-Instruct, is tailored for image captioning and vision-language attribution, focusing on precise, descriptive captions of visual properties, object attributes, and scene details. In contrast, Qwen2.5-VL-7B-Abliterated-Caption-it is fine-tuned for abliterated captioning, generating highly detailed descriptions across diverse visual categories.
Models🤗
✦ DeepCaption-VLA-7B : https://huggingface.co/prithivMLmods/DeepCaption-VLA-7B
✦ Qwen2.5-VL-7B-Abliterated-Caption-it : https://huggingface.co/prithivMLmods/Qwen2.5-VL-7B-Abliterated-Caption-it
Spaces⛵
➜ VisionScope-R2 : https://huggingface.co/spaces/prithivMLmods/VisionScope-R2
➜ Qwen2.5-VL-Outpost : https://huggingface.co/spaces/prithivMLmods/Qwen2.5-VL-Outpost
Collection🗞️
`DeepCaption attr.` : https://huggingface.co/collections/prithivMLmods/deepcaption-attr-68b041172ebcb867e45c556a
`VL Abliterated-Caption` : https://huggingface.co/collections/prithivMLmods/vl-abliterated-caption-68a0443b63182e97a15c47a3
`Multimodal VLMs - Until July'25` : https://huggingface.co/collections/prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
Multimodal VLMs - Aug'25 : https://huggingface.co/collections/prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
GitHub↗️
> DeepCaption-VLA-7B [4bit-notebook demo] : https://github.com/PRITHIVSAKTHIUR/Multimodal-Outpost-Notebooks/blob/main/DeepCaption-VLA-7B%5B4bit%20-%20notebook%20demo%5D/DeepCaption-VLA-7B.ipynb
> Qwen2.5-VL-3B-Abliterated-Caption-it(caption) : https://github.com/PRITHIVSAKTHIUR/Multimodal-Outpost-Notebooks/blob/main/Qwen2.5-VL-3B-Abliterated-Caption-it(caption)/Qwen2_5_VL_3B_Abliterated_Caption_it.ipynb
The community GPU grant was given by Hugging Face — special thanks to them. 🤗🚀
To know more about it, visit the app page or the respective model page!!
reacted
to
Lewdiculous's
post
with ❤️
about 2 months ago
More context for your Pascal GPU or older!
Update: Now available in the official releases of KoboldCpp!
[releases] https://github.com/LostRuins/koboldcpp/releases/latest
These are great news for all the users with GTX 10XX, P40...
Flash Attention implementation for older NVIDIA GPUs without requiring Tensor Cores has come to llama.cpp in the last few days, and should be merged in the next version of KoboldCpp, you can already try it with another fork or by building it.
[Mentioned KCPP fork] https://github.com/Nexesenex/kobold.cpp/releases/latest
[PR] https://github.com/ggerganov/llama.cpp/pull/7188
You should expect less VRAM usage for the same context, allowing you to experience higher contexts with your current GPU.
There have also been reported final tokens/second speed improvements for inference, so that's also grand!
If you have tried it, I'd like to hear your experiences with --flashattention so far, especially for this implementation and for the large number of Pascal (GTX 10XX, P40...) cards.
Discussion linked bellow, with more links to relevant information:
https://huggingface.co/LWDCLS/LLM-Discussions/discussions/11
Cheers!
Organizations
