Post
2896
Good news, llama.cpp seems to be close to supporting MTP on qwen models. Bad news, every single gguf will have to be redone when it is.
- 1 reply
Muhammad.Yahya
myahya8623
AI & ML interests
Deep Learning, Machine Learning and Coding
Recent Activity
reacted to Keeby-smilyai's post with 🤝 about 2 months ago
Hello everyone! reacted to Keeby-smilyai's post with 🤗 about 2 months ago
Hello everyone!Organizations
None yet
reacted to BlueNipples's post with 👀 3 days ago
reacted to Keeby-smilyai's post with 🤝🤗 about 2 months ago
Post
3163
Hello everyone!
- 1 reply
updated a
Space 4 months ago
published a
Space 4 months ago
liked a
model 4 months ago
reacted to JLouisBiz's post with 👍 4 months ago
Post
1968
I’ve built two Firefox extensions for my personal workflow:
1. **Quick Edit in Emacs**
I manage over 3,500 web pages locally. With this extension, I can now click anywhere on a webpage and instantly jump into Emacs to edit the exact page (or annotate any other page I'm working on).
2. **Describe Images (and soon Videos) on the Web**
Using the right-click menu, I can generate descriptions for images I come across online. These descriptions are stored and reused for my own image collections or web pages. I’m planning to add the same functionality for videos soon.
What makes this possible is running LLMs locally on my own machine — I’ve been experimenting with models like **Mistral Vibe** and others. This lets me automate description generation and text processing entirely offline, keeping everything fast, private, and fully under my control.
1. **Quick Edit in Emacs**
I manage over 3,500 web pages locally. With this extension, I can now click anywhere on a webpage and instantly jump into Emacs to edit the exact page (or annotate any other page I'm working on).
2. **Describe Images (and soon Videos) on the Web**
Using the right-click menu, I can generate descriptions for images I come across online. These descriptions are stored and reused for my own image collections or web pages. I’m planning to add the same functionality for videos soon.
What makes this possible is running LLMs locally on my own machine — I’ve been experimenting with models like **Mistral Vibe** and others. This lets me automate description generation and text processing entirely offline, keeping everything fast, private, and fully under my control.
liked a
Space 5 months ago
liked 2
models 5 months ago
upvoted a collection 6 months ago
liked a
Space 6 months ago
moonshotai/Kimi-K2-Thinking
❤️ 35
6
#5985 opened 6 months ago
by 
davanstrien
updated a
Space 8 months ago
liked a
Space 8 months ago
[Cache Request] openai/whisper-large-v3
#555 opened 8 months ago
by myahya8623
upvoted a changelog 8 months ago
Hugging Face Changelog
Custom Domains for Spaces
• 85
liked 2
Spaces 8 months ago
reacted to danielhanchen's post with ❤️ 9 months ago
Post
6649
Run DeepSeek-V3.1 locally on 170GB RAM with Dynamic 1-bit GGUFs!🐋
GGUFs: unsloth/DeepSeek-V3.1-GGUF
The 715GB model gets reduced to 170GB (-80% size) by smartly quantizing layers.
The 1-bit GGUF passes all our code tests & we fixed the chat template for llama.cpp supported backends.
Guide: https://docs.unsloth.ai/basics/deepseek-v3.1
GGUFs: unsloth/DeepSeek-V3.1-GGUF
The 715GB model gets reduced to 170GB (-80% size) by smartly quantizing layers.
The 1-bit GGUF passes all our code tests & we fixed the chat template for llama.cpp supported backends.
Guide: https://docs.unsloth.ai/basics/deepseek-v3.1