Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper
β’
2506.01939
β’
Published
β’
128
Unofficial Mistral Community
community
AI & ML interests
Unofficial org for community upload of Mistral's Open Source models.
Recent Activity
View all activity
mistral-community's activity
JustinLin610Β
authored
a
paper
4 days ago
danielhanchenΒ
posted
an
update
4 days ago
Post
3062
New DeepSeek-R1-0528 1.65-bit Dynamic GGUF!
Run the model locally even easier! Will fit on a 192GB Macbook and run at 7 tokens/s.
DeepSeek-R1-0528 GGUFs: unsloth/DeepSeek-R1-0528-GGUF
Qwen3-8B DeepSeek-R1-0528 GGUFs: unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
And read our Guide: https://docs.unsloth.ai/basics/deepseek-r1-0528
Run the model locally even easier! Will fit on a 192GB Macbook and run at 7 tokens/s.
DeepSeek-R1-0528 GGUFs: unsloth/DeepSeek-R1-0528-GGUF
Qwen3-8B DeepSeek-R1-0528 GGUFs: unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
And read our Guide: https://docs.unsloth.ai/basics/deepseek-r1-0528
Post
5390
Today, we're unveiling two new open-source AI robots! HopeJR for $3,000 & Reachy Mini for $300 π€π€π€
Let's go open-source AI robotics!
Let's go open-source AI robotics!
- 5 replies
Post
3223
It's just become easier to share your apps on the biggest AI app store (aka HF spaces) for unlimited storage, more visibility and community interactions.
Just pick a React, Svelte, or Vue template when you create your space or add
Or follow this link: https://huggingface.co/new-space?sdk=static
Let's build!
Just pick a React, Svelte, or Vue template when you create your space or add
app_build_command: npm run build in your README's YAML and app_file: build/index.html in your README's YAML block.Or follow this link: https://huggingface.co/new-space?sdk=static
Let's build!
- 1 reply
Post
3489
Playing with Veo3 this morning. Share your prompt if you want me to create videos for you (bonus point if they funnily reference HF/open-source). These videos are "a cat on the moon rapping "I love Hugging Face""!
- 25 replies
Post
3675
hey hey
@mradermacher
- VB from Hugging Face here, we'd love to onboard you over to our optimised xet backend! π₯
as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!
in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.
p.s. you'd need to have a the latest hf_xet version of huggingface_hub lib but everything else should be the same: https://huggingface.co/docs/hub/storage-backends#using-xet-storage
p.p.s. this is fully backwards compatible so everything will work as it should! π€
as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!
in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.
p.s. you'd need to have a the latest hf_xet version of huggingface_hub lib but everything else should be the same: https://huggingface.co/docs/hub/storage-backends#using-xet-storage
p.p.s. this is fully backwards compatible so everything will work as it should! π€
- 16 replies
JustinLin610Β
authored
a
paper
21 days ago
JustinLin610Β
authored
a
paper
22 days ago
Post
4061
What are you using to evaluate models or AI systems? So far we're building lighteval & leaderboards on the hub but still feels early & a lot more to build. What would be useful to you?
- 6 replies
mrfakenameΒ
posted
an
update
about 1 month ago
Post
3393
Hi everyone,
I just launched TTS Arena V2 - a platform for benchmarking TTS models by blind A/B testing. The goal is to make it easy to compare quality between open-source and commercial models, including conversational ones.
What's new in V2:
- **Conversational Arena**: Evaluate models like CSM-1B, Dia 1.6B, and PlayDialog in multi-turn settings
- **Personal Leaderboard**: Optional login to see which models you tend to prefer
- **Multi-speaker TTS**: Random voices per generation to reduce speaker bias
- **Performance Upgrade**: Rebuilt from Gradio β Flask. Much faster with fewer failed generations.
- **Keyboard Shortcuts**: Vote entirely via keyboard
Also added models like MegaTTS 3, Cartesia Sonic, and ElevenLabs' full lineup.
I'd love any feedback, feature suggestions, or ideas for models to include.
TTS-AGI/TTS-Arena-V2
I just launched TTS Arena V2 - a platform for benchmarking TTS models by blind A/B testing. The goal is to make it easy to compare quality between open-source and commercial models, including conversational ones.
What's new in V2:
- **Conversational Arena**: Evaluate models like CSM-1B, Dia 1.6B, and PlayDialog in multi-turn settings
- **Personal Leaderboard**: Optional login to see which models you tend to prefer
- **Multi-speaker TTS**: Random voices per generation to reduce speaker bias
- **Performance Upgrade**: Rebuilt from Gradio β Flask. Much faster with fewer failed generations.
- **Keyboard Shortcuts**: Vote entirely via keyboard
Also added models like MegaTTS 3, Cartesia Sonic, and ElevenLabs' full lineup.
I'd love any feedback, feature suggestions, or ideas for models to include.
TTS-AGI/TTS-Arena-V2
- 4 replies
Post
1657
LeRobot-worldwide-hackathon
is already scheduled in 30 cities all over the world! Check if there's one in your city here: LeRobot-worldwide-hackathon/worldwide-map
Post
1544
The
meta-llama
org just crossed 40,000 followers on Hugging Face. Grateful for all their impact on the field sharing the Llama weights openly and much more!
We need more of this from all other big tech to make the AI more open, collaborative and beneficial to all!
meta-llama
org just crossed 40,000 followers on Hugging Face. Grateful for all their impact on the field sharing the Llama weights openly and much more! We need more of this from all other big tech to make the AI more open, collaborative and beneficial to all!
danielhanchenΒ
posted
an
update
about 1 month ago
Post
1886
π Qwen3 128K Context Length: We've released Dynamic 2.0 GGUFs + 4-bit safetensors!
Fixed: Now works on any inference engine and fixed issues with the chat template.
Qwen3 GGUFs:
30B-A3B: unsloth/Qwen3-30B-A3B-GGUF
235-A22B: unsloth/Qwen3-235B-A22B-GGUF
32B: unsloth/Qwen3-32B-GGUF
Read our guide on running Qwen3 here: https://docs.unsloth.ai/basics/qwen3-how-to-run-and-finetune
128K Context Length:
30B-A3B: unsloth/Qwen3-30B-A3B-128K-GGUF
235-A22B: unsloth/Qwen3-235B-A22B-128K-GGUF
32B: unsloth/Qwen3-32B-128K-GGUF
All Qwen3 uploads: unsloth/qwen3-680edabfb790c8c34a242f95
Fixed: Now works on any inference engine and fixed issues with the chat template.
Qwen3 GGUFs:
30B-A3B: unsloth/Qwen3-30B-A3B-GGUF
235-A22B: unsloth/Qwen3-235B-A22B-GGUF
32B: unsloth/Qwen3-32B-GGUF
Read our guide on running Qwen3 here: https://docs.unsloth.ai/basics/qwen3-how-to-run-and-finetune
128K Context Length:
30B-A3B: unsloth/Qwen3-30B-A3B-128K-GGUF
235-A22B: unsloth/Qwen3-235B-A22B-128K-GGUF
32B: unsloth/Qwen3-32B-128K-GGUF
All Qwen3 uploads: unsloth/qwen3-680edabfb790c8c34a242f95
danielhanchenΒ
posted
an
update
about 1 month ago
Post
5826
π¦₯ Introducing Unsloth Dynamic v2.0 GGUFs!
Our v2.0 quants set new benchmarks on 5-shot MMLU and KL Divergence, meaning you can now run & fine-tune quantized LLMs while preserving as much accuracy as possible.
Llama 4: unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
DeepSeek-R1: unsloth/DeepSeek-R1-GGUF-UD
Gemma 3: unsloth/gemma-3-27b-it-GGUF
We made selective layer quantization much smarter. Instead of modifying only a subset of layers, we now dynamically quantize all layers so every layer has a different bit. Now, our dynamic method can be applied to all LLM architectures, not just MoE's.
Blog with Details: https://docs.unsloth.ai/basics/dynamic-v2.0
All our future GGUF uploads will leverage Dynamic 2.0 and our hand curated 300Kβ1.5M token calibration dataset to improve conversational chat performance.
For accurate benchmarking, we built an evaluation framework to match the reported 5-shot MMLU scores of Llama 4 and Gemma 3. This allowed apples-to-apples comparisons between full-precision vs. Dynamic v2.0, QAT and standard iMatrix quants.
Dynamic v2.0 aims to minimize the performance gap between full-precision models and their quantized counterparts.
Our v2.0 quants set new benchmarks on 5-shot MMLU and KL Divergence, meaning you can now run & fine-tune quantized LLMs while preserving as much accuracy as possible.
Llama 4: unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
DeepSeek-R1: unsloth/DeepSeek-R1-GGUF-UD
Gemma 3: unsloth/gemma-3-27b-it-GGUF
We made selective layer quantization much smarter. Instead of modifying only a subset of layers, we now dynamically quantize all layers so every layer has a different bit. Now, our dynamic method can be applied to all LLM architectures, not just MoE's.
Blog with Details: https://docs.unsloth.ai/basics/dynamic-v2.0
All our future GGUF uploads will leverage Dynamic 2.0 and our hand curated 300Kβ1.5M token calibration dataset to improve conversational chat performance.
For accurate benchmarking, we built an evaluation framework to match the reported 5-shot MMLU scores of Llama 4 and Gemma 3. This allowed apples-to-apples comparisons between full-precision vs. Dynamic v2.0, QAT and standard iMatrix quants.
Dynamic v2.0 aims to minimize the performance gap between full-precision models and their quantized counterparts.
Post
4027
Energy is a massive constraint for AI but do you even know what energy your chatGPT convos are using?
We're trying to change this by releasing ChatUI-energy, the first interface where you see in real-time what energy your AI conversations consume. Great work from @jdelavande powered by spaces & TGI, available for a dozen of open-source models like Llama, Mistral, Qwen, Gemma and more.
jdelavande/chat-ui-energy
Should all chat interfaces have this? Just like ingredients have to be shown on products you buy, we need more transparency in AI for users!
We're trying to change this by releasing ChatUI-energy, the first interface where you see in real-time what energy your AI conversations consume. Great work from @jdelavande powered by spaces & TGI, available for a dozen of open-source models like Llama, Mistral, Qwen, Gemma and more.
jdelavande/chat-ui-energy
Should all chat interfaces have this? Just like ingredients have to be shown on products you buy, we need more transparency in AI for users!
-
- 3 replies
Post
2976
Just crossed half a million public apps on Hugging Face. A new public app is created every minute these days π€―π€―π€―
What's your favorite? http://hf.co/spaces
What's your favorite? http://hf.co/spaces
- 3 replies
Post
1481
You can now bill your inference costs from all our inference partners (together, fireworks, fal, sambanova, cerebras, hyperbolic,...) to your Hugging Face organization.
Useful to drive more company-wide usage of AI without the billing headaches!
Useful to drive more company-wide usage of AI without the billing headaches!
- 1 reply