Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

LLM, LORA, text generation, prompt-tuning

Recent Activity

lu-vaeย  authored a paper 6 days ago
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
lu-vaeย  authored a paper 6 days ago
Virtual Width Networks
lu-vaeย  authored a paper 6 days ago
STEP3-VL-10B Technical Report
View all activity

prithivMLmodsย 
posted an update 2 days ago
view post
Post
2233
Dropping the Qwen3 VL Series of Unredacted MAX-VL models. These models have undergone multi-stage training to minimize refusal rates through continuous abliterated optimization. You can find the models in BF16, FP8-Dynamic, and GGUF formats at the links below.๐Ÿ”ฅ๐Ÿš€

Unredacted MAX - VL:
โžœ prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX
โžœ prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX
โžœ prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX
โžœ prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX

Unredacted MAX - VL [FP8]
โžœ prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX-FP8
โžœ prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX-FP8
โžœ prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX-FP8
โžœ prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-FP8

Unredacted MAX - VL [GGUF]
โžœ prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX-GGUF
โžœ prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX-GGUF
โžœ prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX-GGUF
โžœ prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF

Unredacted MAX - VL [Collection]
โžœ https://huggingface.co/collections/prithivMLmods/unredacted-max-vl-fp8
โžœ https://huggingface.co/collections/prithivMLmods/unredacted-max-vl
โžœ https://huggingface.co/collections/prithivMLmods/unredacted-max-vl-gguf

To learn more, visit the app page or the respective model pages.
Ujjwal-Tyagiย 
posted an update 2 days ago
view post
Post
157
Qwen 3.5 Model is here! Supporting 1m context length by default, It is giving much good performance and competitive to Claude Opus 4.6, Qwen/Qwen3.5-397B-A17B, here it's GGUF: unsloth/Qwen3.5-397B-A17B-GGUF, Follow me and turn on the notification for the latest news!
lu-vaeย 
authored 4 papers 6 days ago
Ujjwal-Tyagiย 
posted an update 6 days ago
view post
Post
2949
GLM 5 is insane, it ranks #4 Globally!
ยท
prithivMLmodsย 
posted an update 10 days ago
view post
Post
2878
Introducing FLUX.2-Klein-LoRA-Studio, a demo for image editing using specialized LoRA adapters built for the FLUX.2-Klein-Distilled model. It features an edit-style gallery for multi-style image editing, including de-light, face swap, mannequin, and more. Try the demo below.

๐Ÿค—Demo: prithivMLmods/FLUX.2-Klein-LoRA-Studio
๐Ÿค—Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
๐Ÿค—GitHub: https://github.com/PRITHIVSAKTHIUR/FLUX.2-Klein-LoRA-Studio

To learn more, visit the app page or the respective model pages.
prithivMLmodsย 
posted an update 13 days ago
view post
Post
835
GLM OCR, a multimodal OCR model for complex document understanding, built on the GLM-V encoderโ€“decoder architecture. It delivers high accuracy and strong generalization with a blazing-fast inference pipeline. The demo is live . Try it now. ๐Ÿค—๐Ÿš€

โœจ Demo: prithivMLmods/GLM-OCR-Demo
โœจ Multimodal Implementations: https://huggingface.co/collections/prithivMLmods/multimodal-implementations
โœจ GitHub: https://github.com/PRITHIVSAKTHIUR/GLM-OCR-Demo
prithivMLmodsย 
posted an update 15 days ago
view post
Post
2145
Introducing the Qwen-Image-Edit-3D-Lighting-Control app, featuring 8ร— horizontal and 3ร— elevational lighting positions for precise 3D lighting control. It enables studio-level lighting using fast Qwen Image Edit fast inference, paired with Multi-Angle-Lighting adapters. ๐Ÿ”ฆ

๐Ÿ”ฅ Space: prithivMLmods/Qwen-Image-Edit-3D-Lighting-Control
โœ… Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
๐Ÿ“‚ GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-Edit-3D-Lighting-Control
prithivMLmodsย 
posted an update 20 days ago
view post
Post
3630
Daggr UI version of the Qwen3-TTS demo.๐Ÿ”ฅ
(custom voice, voice design, qwen3-asr and voice cloning) nodes.
No remote spaces used for API inference; all functions run in-app fn.
Powered by t4-m and built with daggr@0.5.2 and gradio@6.

๐Ÿ‘‰Demo: prithivMLmods/Qwen3-TTS-Daggr-UI
โญGithub: https://github.com/PRITHIVSAKTHIUR/Qwen3-TTS-Daggr-UI
  • 1 reply
ยท
Ujjwal-Tyagiย 
posted an update 21 days ago
prithivMLmodsย 
posted an update 23 days ago
view post
Post
2685
Qwen-Image-Edit-Object-Manipulator Space is now featured in Hugging Face Space of the Week. It enables object manipulation such as extracting objects, adding designs, and removing objects or designs from the red highlighted area using specialized adapters.

๐Ÿ”ฅDo enjoy the demo! ~ prithivMLmods/Qwen-Image-Edit-Object-Manipulator

Collections:
๐ŸงจAdapters-1: https://huggingface.co/collections/prithivMLmods/qwen-image-edit-exps
๐ŸงจAdapters-2: https://huggingface.co/collections/prithivMLmods/qie-jan-23-26
๐ŸงจAdapters-3: https://huggingface.co/collections/prithivMLmods/qwen-image-edit-object-manipulator

โญGithub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-Edit-Object-Manipulator

To learn more, visit the app page or the respective model pages.
  • 1 reply
ยท
prithivMLmodsย 
posted an update 26 days ago
view post
Post
3041
Introducing QIE-2511-Zoom-Master for highlight-guided area zoom-in, enabling lossless zooming within a drawn square area, and QIE-2511-Object-Remover-v2 for precise object or highlight-guided area cleanup. These experimental adapters are trained based on QIE-2511. Find the adapters below.

๐Ÿ•น๏ธQIE-2511-Zoom-Master : prithivMLmods/QIE-2511-Zoom-Master
๐Ÿ•น๏ธQIE-2511-Object-Remover-v2: prithivMLmods/QIE-2511-Object-Remover-v2

๐Ÿค—Demo: prithivMLmods/Qwen-Image-Edit-Object-Manipulator

๐Ÿ“‚Collection: https://huggingface.co/collections/prithivMLmods/qwen-image-edit-exps

To learn more, visit the app page or the respective model pages.
  • 2 replies
ยท
Facicoย 
authored a paper 26 days ago
Facicoย 
submitted a paper to Daily Papers 27 days ago
Ujjwal-Tyagiย 
posted an update 27 days ago
view post
Post
1805
There is a new open-source music generation model called HeartMuLa. It offers strong, competitive performance compared to Suno and supports English, Chinese, Japanese, Korean, and Spanish. It is optimized to run easily on RTX GPUs and other consumer-grade hardware. HeartMuLa/HeartMuLa-oss-3B
https://github.com/HeartMuLa/heartlib
  • 1 reply
ยท
Ujjwal-Tyagiย 
posted an update about 1 month ago
view post
Post
2782
So, Koreans are also doing great progress behind Chinese,
Their two open source ai models that are actually good in coding. upstage/Solar-Open-100B skt/A.X-K1
  • 1 reply
ยท
Ujjwal-Tyagiย 
posted an update about 1 month ago
Ujjwal-Tyagiย 
posted an update about 1 month ago
view post
Post
2600
I am very excited to see the release of nyuuzyou/gitee-code. This is exactly what I have been looking for. Thank you to @nyuuzyou for his hard work on this.
ยท