Hugging Face's logo
Activity Feed

AI & ML interests

Hugging Face Inference Endpoints Images repository allows AI Builders to collaborate and engage creating awesome inference deployments

Recent Activity
AdinaY  submitted a paper 16 days ago
TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification
AdinaY  submitted a paper about 1 month ago
KAT-Coder-V2 Technical Report
AdinaY  submitted a paper about 2 months ago
Training Language Models via Neural Cellular Automata
View all activity
qgallouedec 
posted an update 6 days ago
view post
Post
7807

TRL v1.3 ships day-one training support for Qwen 3.6 🚀

The new Qwen 3.6 family (Qwen/Qwen3.6-27B, Qwen/Qwen3.6-35B-A3B) reuses the Qwen3.5-MoE architecture but ships a slightly different chat template, so we updated the stack end-to-end: new training template with {% generation %} markers, tool-call response schema routing, tiny test models for the VLM matrix.

SFT with assistant-only loss works out of the box:

from trl import SFTConfig, SFTTrainer

trainer = SFTTrainer(
    model="Qwen/Qwen3.6-27B",
    args=SFTConfig(assistant_only_loss=True),
    train_dataset=dataset,
)
trainer.train()


So does GRPO tool-calling — just hand tools=[...] to GRPOTrainer.

v1.3 also brings a new experimental TPO trainer (Triple Preference Optimization), speculative decoding in trl vllm-serve (Qwen3 MTP / Eagle3 drafts), 12 more KTO ↔ DPO alignment PRs (KTO promotion to stable is now in reach), three more {% generation %} chat templates (Gemma/Gemma 2, Phi-3, GLM-4-MoE), and a chunky SFT entropy bug fix.

Full release notes: https://github.com/huggingface/trl/releases/tag/v1.3.0
AdinaY 
submitted a paper to Daily Papers 16 days ago
qgallouedec 
posted an update 16 days ago
view post
Post
1895
TRL v1.2 introduces the SSDTrainer 🚀

Simple Self-Distillation (SSD) from Apple's paper "Embarrassingly Simple Self-Distillation Improves Code Generation" is now available as an experimental trainer in TRL.

The recipe is as minimal as the name suggests: sample completions from the model itself at a training-time temperature, then fine-tune on those raw, unverified samples with plain cross-entropy. No reward model. No verifier. No teacher model. No reinforcement learning. Just prompts and the model.

from trl.experimental.ssd import SSDConfig, SSDTrainer

trainer = SSDTrainer(
    model="Qwen/Qwen3-4B-Instruct",
    args=SSDConfig(temperature=0.6, top_k=20, top_p=0.95),
    train_dataset=dataset,
)
trainer.train()


v1.2 also ships expanded tool-calling support (LLaMA 3.1 / 3.2, DeepSeek-V3), another round of KTO ↔ DPO alignment getting us closer to promoting KTO to stable, a big GRPO simplification for overlong tool results, deprecation of use_transformers_paged, and key fixes for VLM response parsing.

Full release notes: https://github.com/huggingface/trl/releases/tag/v1.2.0
qgallouedec 
posted an update about 1 month ago
view post
Post
2380
TRL v1.0 is out!

Hugging Face's TRL library is downloaded 3 million times a month. Over 130k models trained with it are public on the Hub, and major projects like @unsloth and @axolotl-ai-co build directly on top of it. v1.0 is the moment we acknowledged that responsibility explicitly, with a real stability contract.

The field hasn't settled. Building stable software in a domain that keeps invalidating its own assumptions is the actual problem we're solving. The answer is a design that can absorb the next shift without breaking what people rely on.

What's in v1.0:
Deep Hugging Face integration, low infrastructure burden
What's next: asynchronous GRPO, better scaling support, and making training legible enough that agents can inspect and steer it.

pip install --upgrade trl


Read more: hf.co/blog/trl-v1
AdinaY 
submitted a paper to Daily Papers about 1 month ago
AdinaY 
submitted 2 papers to Daily Papers about 2 months ago
alvarobartt 
posted an update about 2 months ago
view post
Post
3678
Learn how to deploy Microsoft Research VibeVoice ASR on Microsoft Azure Foundry with Hugging Face to generate rich audio transcriptions with Who, When, and What! 💥

> 🕒 60-minute single-pass processing, no chunking or stitching
> 👤 Customized hotwords to guide recognition on domain-specific content
> 📝 Rich transcription: joint ASR + diarization + timestamping in one pass
> 🌍 50+ languages with automatic detection and code-switching support
> 🤗 Deployed on Microsoft Foundry via an OpenAI-compatible Chat Completions API

https://huggingface.co/docs/microsoft-azure/foundry/examples/deploy-vibevoice-asr
qgallouedec 
posted an update 2 months ago
view post
Post
3036
@CohereLabs just released 🌿 Tiny Aya: a fully open-source 3B parameter model that speaks 70+ languages 🌍! But there’s a catch:

Tiny Aya is just a language model. It doesn’t support tool calling, the key capability that turns frontier models into powerful *agents*.
So the real question is:

How hard is it to turn Tiny Aya into an agent?

Turns out… it’s simple, thanks to Hugging Face TRL.
We’re sharing a hands-on example showing how to train Tiny Aya to turn it into a tool-calling agent using TRL, unlocking what could become the first *massively multilingual open agent*.

Small model. Global reach. Agent capabilities.

👉 https://github.com/huggingface/trl/blob/main/examples/notebooks/sft_tool_calling.ipynb
  • 1 reply
·
AdinaY 
posted an update 3 months ago
view post
Post
3746
MiniMax M2.5 is now available on the hub 🚀

MiniMaxAI/MiniMax-M2.5

✨ 229B - Modified MIT license
✨37% faster than M2.1
✨ ~$1/hour at 100 TPS
  • 2 replies
·
AdinaY 
posted an update 3 months ago
AdinaY 
posted an update 3 months ago
view post
Post
4178
Game on 🎮🚀

While Seedance 2.0’s videos are all over the timeline, DeepSeek quietly pushed a new model update in its app.

GLM-5 from Z.ai adds more momentum.

Ming-flash-omni from Ant Group , MiniCPM-SALA from OpenBMB
, and the upcoming MiniMax M2.5 keep the heat on 🔥

Spring Festival is around the corner,
no one’s sleeping!

✨ More releases coming, stay tuned
https://huggingface.co/collections/zh-ai-community/2026-february-china-open-source-highlights
AdinaY 
posted an update 3 months ago
view post
Post
3961
Ming-flash-omni 2.0 🚀 New open omni-MLLM released by Ant Group

inclusionAI/Ming-flash-omni-2.0

✨ MIT license
✨ MoE - 100B/6B active
✨ Zero-shot voice cloning + controllable audio
✨ Fine-grained visual knowledge grounding
  • 2 replies
·
AdinaY 
posted an update 3 months ago
view post
Post
815
LLaDA 2.1 is out 🔥 A new series of MoE diffusion language model released by AntGroup

inclusionAI/LLaDA2.1-mini
inclusionAI/LLaDA2.1-flash

✨LLaDA2.1-mini: 16B - Apache2.0
✨LLaDA2.1-flash: 100B - Apache2.0
✨Both delivers editable generation, RL-trained diffusion reasoning and fast inference
  • 2 replies
·
AdinaY 
posted an update 3 months ago
view post
Post
2630
AI for science is moving fast🚀

Intern-S1-Pro 🔬 a MoE multimodal scientific reasoning model from Shanghai AI Lab

internlm/Intern-S1-Pro

✨ 1T total / 22B active
✨ Apache 2.0
✨ SoTA scientific reasoning performance
✨ FoPE enables scalable modeling of long physical time series (10⁰–10⁶)
  • 2 replies
·
AdinaY 
posted an update 3 months ago
view post
Post
1420
✨ China’s open source AI ecosystem has entered a new phase

https://huggingface.co/blog/huggingface/one-year-since-the-deepseek-moment-blog-3

One year after the “DeepSeek Moment,” open source has become the default. Models, research, infrastructure, and deployment are increasingly shared to support large-scale, system-level integration.

This final blog examines how leading Chinese AI organizations are evolving ,and what this implies for the future of open source.
AdinaY 
posted an update 3 months ago
view post
Post
417
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)
AdinaY 
posted an update 3 months ago
view post
Post
1626
Step 3.5 Flash 🔥 new foundation model from StepFun ai

https://huggingface.co/collections/stepfun-ai/step-35-flash

✨ Sparse MoE：196B/11B active
✨ Supports up to 256K context
✨ Multi-token prediction for fast decoding (100–300 tok/s)
✨ Runs locally on consumer hardware
AdinaY 
posted an update 3 months ago
view post
Post
1141
What a week 🤯

Following DeepSeek, Kimi, Qwen, Baidu, and Ant Group, Unitree Robotics
has now released a VLA model on the hub too!

unitreerobotics/UnifoLM-VLA-Base
alvarobartt 
posted an update 3 months ago
view post
Post
3242
💥 hf-mem v0.4.1 now also estimates KV cache memory requirements for any context length and batch size with the --experimental flag!

uvx hf-mem --model-id ... --experimental will automatically pull the required information from the Hugging Face Hub to include the KV cache estimation, when applicable.

💡 Alternatively, you can also set the --max-model-len, --batch-size and --kv-cache-dtype arguments (à la vLLM) manually if preferred.
  • 1 reply
·