Hugging Face's logo

CyberHarem
community
Activity Feed Request to join this org

AI & ML interests

Anime Bishojo. This organization is only for waifus' datasets and loras
CharlieDreemurΒ 
authored 3 papers 3 months ago
s3nhΒ 
posted an update 4 months ago
view post
Post
576
Uncensoring Mistral,

give it a try
s3nh/Ministral-3-14B-Instruct-2512-BF16-abliterated
s3nhΒ 
posted an update 5 months ago
view post
Post
614
Existing methods β€” GPTQ, AWQ, llama.cpp's k-quants β€” minimize empirical loss heuristically. None of them prove they are optimal in any information-theoretic sense. ICRB-Q builds a quantization scheme that is provably optimal via the CramΓ©r-Rao lower bound (CRB): no unbiased estimator of a weight can have lower variance than [F(ΞΈ)]⁻¹, where F is the Fisher information matrix.
  • 1 reply
Β·
CharlieDreemurΒ 
authored a paper 10 months ago
adamm-hfΒ 
posted an update about 1 year ago
adamm-hfΒ 
posted an update about 1 year ago
view post
Post
925
The new King πŸ‘‘has arrived!

Moonshot AI now the top model on Hugging Face πŸ”₯
moonshotai/Kimi-K2-Thinking
adamm-hfΒ 
posted an update about 1 year ago
view post
Post
2,952
πŸ’ΈπŸ€‘You don’t need 100 GPUs to train something amazing!

Our Smol Training Playbook teaches you a better path to world-class LLMs, for free!

Check out the #1 trending space on πŸ€— :
HuggingFaceTB/smol-training-playbook
s3nhΒ 
posted an update about 1 year ago
view post
Post
952
Eduhelp with more empathy, based on model finetuned on
psychotheraputic preferences just landed on


Beck-8B as a base model, 13000 steps on educational dataset.
Time to go further and build more πŸ₯°
s3nh/EduHelp_Beck_8B
Thanks to @basilic_ai for computations <3
s3nhΒ 
posted an update about 1 year ago
view post
Post
4,433
Just tried to create an educational assistant for younger people who can struggle with visualsation of 'what is this sorcery all about'.
Its first step of my spare time projects, sft on Qwen3-8B,

EduHelper is a child-friendly tutoring assistant fine-tuned from the Qwen3-8B base model using parameter-efficient fine-tuning (PEFT) with LoRA on the ajibawa-2023/Education-Young-Children dataset.

s3nh/EduHelp-8B

Glad to share my work, have a wonderful day!
  • 2 replies
Β·
adamm-hfΒ 
posted an update about 1 year ago
view post
Post
2,415
Cool stuff these past weeks on huggingface! πŸ€— πŸš€ !
β€’ πŸ“ˆTrackio, local-first W&B alternative
https://github.com/gradio-app/trackio/issues
β€’ 🌍EmbeddingGemma, 300M-param, multilingual embeddings, on-device
https://huggingface.co/blog/embeddinggemma
β€’ πŸ’»Open LLMs in VS Code (Inference Providers)
https://x.com/reach_vb/status/1966185427582497171
β€’ πŸ€–Smol2Operator GUI agents
https://huggingface.co/blog/smol2operator
β€’ πŸ–ΌοΈGradio visible watermarking
https://huggingface.co/blog/watermarking-with-gradio
narugo1992Β 
in CyberHarem/makima_nikke over 1 year ago

Model Running Help

5
#1 opened over 1 year ago by
Amir1387aht
ameerazam08Β 
posted an update almost 2 years ago
s3nhΒ 
posted an update almost 2 years ago
view post
Post
2,556
Welcome back,

Small Language Models Enthusiasts and GPU Poor oss enjoyers lets connect.
Just created an organization which main target is to have fun with smaller models tuneable on consumer range GPUs, feel free to join and lets have some fun, much love ;3

SmolTuners
  • 3 replies
Β·
adamm-hfΒ 
posted an update almost 2 years ago
anohaΒ 
updated a Space about 2 years ago
narugo1992Β 
updated 3 models about 2 years ago