Ibrahim.H
bitsnaps
AI & ML interests
Text mining, sentiment analysis, text summarization
Recent Activity
upvoted a paper 25 minutes ago
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries liked a model about 12 hours ago
MiniMaxAI/MiniMax-Music3 reacted to JonathanColetti's post with 🔥 about 12 hours ago
I just uncensored qwen 3.8 27B. You can check out the demo here: https://huggingface.co/spaces/JonathanColetti/Qwen3.8-27B-Uncensored-Demo or the full repo: https://huggingface.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF
What I did was used an H100 NVL and use https://github.com/p-e-w/heretic to uncensor it. I measured the KL divergence and the refusal rate (Refusal rate is the count of refusals over 100 hold out prompts from mlabonne/harmful_behaviors). Check out the full repo and give it a like if you think its cool
Thanks!Organizations
increase the max_new_tokens in the demo
#33 opened 6 months ago
by bitsnaps
Create app.py
#1 opened 11 months ago
by bitsnaps
Space stuck in "Preparing Space"
2
#9 opened 12 months ago
by 
eienmojiki
[FEEDBACK] Inference Providers
❤️ 20
170
#49 opened over 1 year ago
by 
julien-c
Bad request: AutoPipeline can't find a pipeline linked to StableCascadeDecoderPipeline for None
👍 8
1
#18 opened over 2 years ago
by 
miniwater
Error running the code:
1
#29 opened about 3 years ago
by 
Andyrasika
TypeError: RefinedWebModel isn't supported yet.
9
#1 opened about 3 years ago
by 
thefaheem
i am getting error
5
#37 opened over 3 years ago
by 
saif9002
i am getting error
5
#37 opened over 3 years ago
by saif9002