s3nh/Nanbeige-4.1-3B-Uncensored
Text Generation • 4B • Updated • 301
s3nh PRO
s3nh
AI & ML interests
Quantization, LLMs, Deep Learning for good. Follow me if you like my work. Patreon.com/s3nh
Recent Activity
updated a model 7 days ago
s3nh/Nanbeige-4.1-3B-Uncensored updated a model 7 days ago
s3nh/SmolLLM-3B-Uncensored published a model 7 days ago
s3nh/SmolLLM-3B-UncensoredOrganizations
updated 2
models 7 days ago
published 2
models 7 days ago
liked a
model 7 days ago
upvoted an article 7 days ago
Article
Projected Abliteration
•
41
updated a
model 7 days ago
published a
model 7 days ago
reactedto danielhanchen's post with 🚀🔥 11 days ago
Post
2955
You can now fine-tune Qwen3.5 for free with our notebook! 🔥
You just need 5GB VRAM to train Qwen3.5-2B LoRA locally!
Unsloth trains Qwen3.5 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/models/qwen3.5/fine-tune
Qwen3.5-4B Colab: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_5_(4B)_Vision.ipynb
You just need 5GB VRAM to train Qwen3.5-2B LoRA locally!
Unsloth trains Qwen3.5 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/models/qwen3.5/fine-tune
Qwen3.5-4B Colab: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_5_(4B)_Vision.ipynb
liked 2
models 11 days ago
reactedto mitkox's post with 🚀 about 1 month ago
Post
339
134,614 tok/sec input prefil max
1031 tokens/sec out gen max
At these local AI speeds, there is no User Interface for humans. My human UI is the Radicle distributed Git issues queue
On my GPU workstation:
- Z8 Fury G5 4x A6000
- MiniMax-M2.5
- Claude Code to localhost:8000
1031 tokens/sec out gen max
At these local AI speeds, there is no User Interface for humans. My human UI is the Radicle distributed Git issues queue
On my GPU workstation:
- Z8 Fury G5 4x A6000
- MiniMax-M2.5
- Claude Code to localhost:8000
- 1 reply
liked a
model about 1 month ago
reactedto Tonic's post with 🔥 about 1 month ago
Post
3311
🙋🏻♂️hello my lovelies ,
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : Tonic/hugging-claw (use git clone to inspect)
literally the one-click link : Tonic/hugging-claw
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : Tonic/hugging-claw (use git clone to inspect)
literally the one-click link : Tonic/hugging-claw
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
- 2 replies
reactedto MonsterMMORPG's post with 🔥 about 1 month ago
Post
2986
SECourses Musubi Trainer upgraded to V27 and FLUX 2, FLUX Klein, Z-Image training added with demo configs - amazing VRAM optimized - read the news
App is here : https://www.patreon.com/posts/137551634
Full tutorial how to use and train : https://youtu.be/DPX3eBTuO_Y
App is here : https://www.patreon.com/posts/137551634
Full tutorial how to use and train : https://youtu.be/DPX3eBTuO_Y
- 1 reply
reactedto codelion's post with 🔥 about 1 month ago
Post
6145
Introducing Dhara-70M: A diffusion language model that achieves 3.8x higher throughput than autoregressive models!
Key findings from our research on optimal architectures for small language models:
→ Depth beats width: 32 layers outperforms 12 layers at the same parameter count
→ Best-in-class factuality: 47.5% on TruthfulQA
→ 10x training efficiency using WSD (Warmup-Stable-Decay) conversion
→ Canon layers add only 0.13% parameters but improve reasoning
We trained on 1B tokens using the optimal 50-30-20 dataset mix (PDFs + filtered web + educational content), then converted to diffusion with just 100M additional tokens.
Blog: https://huggingface.co/blog/codelion/optimal-model-architecture
Model: codelion/dhara-70m
Key findings from our research on optimal architectures for small language models:
→ Depth beats width: 32 layers outperforms 12 layers at the same parameter count
→ Best-in-class factuality: 47.5% on TruthfulQA
→ 10x training efficiency using WSD (Warmup-Stable-Decay) conversion
→ Canon layers add only 0.13% parameters but improve reasoning
We trained on 1B tokens using the optimal 50-30-20 dataset mix (PDFs + filtered web + educational content), then converted to diffusion with just 100M additional tokens.
Blog: https://huggingface.co/blog/codelion/optimal-model-architecture
Model: codelion/dhara-70m
- 1 reply
reactedto giux78's post with 🔥 about 2 months ago
Post
227
Together with @mferraretto and @efederici we released #Nesso-4B, a new model specialized for agentic workflows.
mii-llm/nesso-4B
#Nesso-4B is a fine-tuned version of Qwen-4B, trained on a highly curated and balanced dataset designed specifically for multilingual agentic workflows and conversational use cases.
As shown in the video below we simulate, the new “cowork” from #Antrophic, without any data sharing all running on a consumer device. The model can be used to build agentic behavior in #privateAI environments.
Not every problem requires super intelligence: in many cases, intelligence at the edge is more than enough.
#Nesso4B #AgenticAI #PrivateAI #EdgeAI #OnDeviceAI
mii-llm/nesso-4B
#Nesso-4B is a fine-tuned version of Qwen-4B, trained on a highly curated and balanced dataset designed specifically for multilingual agentic workflows and conversational use cases.
As shown in the video below we simulate, the new “cowork” from #Antrophic, without any data sharing all running on a consumer device. The model can be used to build agentic behavior in #privateAI environments.
Not every problem requires super intelligence: in many cases, intelligence at the edge is more than enough.
#Nesso4B #AgenticAI #PrivateAI #EdgeAI #OnDeviceAI
- 2 replies
reactedto AdinaY's post with 🔥 about 2 months ago
Post
404
GLM just entered the OCR field🔥
zai-org/GLM-OCR
✨ 0.9B
✨ MIT licensed
✨ Multimodal GLM-V architecture
✨ #1 on OmniDocBench v1.5 (94.62)
zai-org/GLM-OCR
✨ 0.9B
✨ MIT licensed
✨ Multimodal GLM-V architecture
✨ #1 on OmniDocBench v1.5 (94.62)
liked a
model about 2 months ago
