KingNish (Nishith Jain)

reacted to burtenshaw's post with ❤️ 7 days ago

Post

3354

The Hugging Face Agents Course now includes three major agent frameworks!

🔗 https://huggingface.co/agents-course

This includes LlamaIndex, LangChain, and our very own smolagents. We've worked to integrate the three frameworks in distinctive ways so that learners can reflect on when and where to use each.

This also means that you can follow the course if you're already familiar with one of these frameworks, and soak up some of the fundamental knowledge in earlier units.

Hopefully, this makes the agents course as open to as many people as possible.

3 replies

·

reacted to chansung's post with ❤️ 8 days ago

Post

2486

Mistral AI Small 3.1 24B is not only commercial free but also the best model in a single GPU deployment.

I packed up all the information you need to know in a single picture. Hope this helps! :)

1 reply

·

reacted to fdaudens's post with 🔥 8 days ago

Post

1877

🔊 Meet Orpheus: A breakthrough open-source TTS model that matches human-level speech with empathy & emotion.
- Available in 4 sizes (150M-3B parameters)
- delivers ultra-fast streaming
- zero-shot voice cloning.
- Apache 2.0 license

canopylabs/orpheus-tts-67d9ea3f6c05a941c06ad9d2

1 reply

·

reacted to mlabonne's post with 🚀 10 days ago

Post

5991

✂️ Gemma 3 Abliterated

I noticed that Gemma 3 was much more resilient to refusal removal than other models like Qwen 2.5.

I experimented with different recipes and improved the abliteration technique I wrote about last year.

It's still experimental but the refusal rate is super low in my tests. Enjoy!

mlabonne/gemma-3-4b-it-abliterated
mlabonne/gemma-3-12b-it-abliterated
mlabonne/gemma-3-27b-it-abliterated

1 reply

·

reacted to KaiChen1998's post with 🔥 12 days ago

Post

4797

📢 Our EMOVA paper has been accepted by CVPR 2025, and we are glad to release all resources, including code (training & inference), datasets (training & evaluation), and checkpoints (EMOVA-3B/7B/72B)!

🤗 EMOVA is a novel end-to-end omni-modal LLM that can see, hear and speak. Given omni-modal (i.e., textual, visual and speech) inputs, EMOVA can generate both textual and speech responses with vivid emotional controls by utilizing the speech decoder and a style controller.

✨ EMOVA Highlights
✅ State-of-the-art omni-modality: EMOVA achieves SoTA comparable results on both vision-language and speech benchmarks simultaneously.
✅ Device adaptation: our codebase supports training/inference on both NVIDIA GPUs (e.g., A800 & H20) and Ascend NPUs (e.g., 910B3)!
✅ Modular design: we integrate multiple implementations of vision encoder, vision projector, and language model, even including the most recent DeepSeekMoE-tiny!

🔥 You are all welcome to try and star!
- Project page: https://emova-ollm.github.io/
- Github: https://github.com/emova-ollm/EMOVA
- Demo: Emova-ollm/EMOVA-demo

reacted to m-ric's post with 🔥🤗 12 days ago

Post

4539

smolagents now support vLLM! 🥳

As one of the most popular local inference solutions, the community had been asking us to integrate vLLM: after a heavy refactoring of our LLM classes, we've just released smolagents 1.11.0, with a brand new VLLMModel class.

Go try it and tell us what you think!

https://github.com/huggingface/smolagents/blob/45b2c86857b7f7657daaa74e4d17d347e9e2c4a4/src/smolagents/models.py#L497

reacted to clem's post with 🤗 12 days ago

Post

4581

We just crossed 1,500,000 public models on Hugging Face (and 500k spaces, 330k datasets, 50k papers). One new repository is created every 15 seconds. Congratulations all!

3 replies

·

reacted to AdinaY's post with 🔥🤗 15 days ago

Post

1901

Open Sora 2.0 is out 🔥
hpcai-tech/open-sora-20-67cfb7efa80a73999ccfc2d5
✨ 11B with Apache2.0
✨ Low training cost - $200k
✨ open weights, code and training workflow

reacted to burtenshaw's post with 🤗 15 days ago

Post

1801

everybody and their dog is fine-tuning Gemma 3 today, so I thought I'd do a longer post on the tips and sharp edges I find. let's go!

1. has to be install everything form main and nightly. this is what I'm working with to get unsloth and TRL running

git+https://github.com/huggingface/transformers@main
git+https://github.com/huggingface/trl.git@main
bitsandbytes
peft

plus this with --no-deps

git+https://github.com/unslothai/unsloth-zoo.git@nightly
git+https://github.com/unslothai/unsloth.git@nightly

2. will brown's code to turn GSM8k into a reasoning dataset is a nice toy experiment https://gist.github.com/willccbb/4676755236bb08cab5f4e54a0475d6fb

3. with a learning rate of 5e-6 rewards and loss stayed flat for the first 100 or so steps.

4. so far none of my runs have undermined the outputs after 1 epoch. therefore, I'm mainly experimenting with bigger LoRA adapters.

from trl import GRPOConfig

training_args = GRPOConfig(
    learning_rate = 5e-6,
    adam_beta1 = 0.9,
    adam_beta2 = 0.99,
    weight_decay = 0.1,
    warmup_ratio = 0.1,
    lr_scheduler_type = "cosine",
    optim = "adamw_8bit",
    logging_steps = 1,
    per_device_train_batch_size = 2,
    gradient_accumulation_steps = 1,
    num_generations = 2,
    max_prompt_length = 256,
    max_completion_length = 1024 - 256,
    num_train_epochs = 1,
    max_steps = 250,
    save_steps = 250,
    max_grad_norm = 0.1,
    report_to = "none",
)

5. vision fine-tuning isn't available in TRL's GRPOTrainer, so stick to text datasets. but no need to load the model differently in transformers or Unsloth

from transformers import AutoModelForImageTextToText

model = AutoModelForImageTextToText.from_pretrained("google/gemma-3-4b-it)

if you want an introduction to GRPO, check out the reasoning course, it walks you through the algorithm, theory, and implementation in a smooth way.

https://huggingface.co/reasoning-course

2 replies

·

reacted to thomwolf's post with 🔥 15 days ago

Post

2625

We've kept pushing our Open-R1 project, an open initiative to replicate and extend the techniques behind DeepSeek-R1.

And even we were mind-blown by the results we got with this latest model we're releasing: ⚡️OlympicCoder ( open-r1/OlympicCoder-7B and open-r1/OlympicCoder-32B)

It's beating Claude 3.7 on (competitive) programming –a domain Anthropic has been historically really strong at– and it's getting close to o1-mini/R1 on olympiad level coding with just 7B parameters!

And the best part is that we're open-sourcing all about its training dataset, the new IOI benchmark, and more in our Open-R1 progress report #3: https://huggingface.co/blog/open-r1/update-3

Datasets are are releasing:
- open-r1/codeforces
- open-r1/codeforces-cots
- open-r1/ioi
- open-r1/ioi-test-cases
- open-r1/ioi-sample-solutions
- open-r1/ioi-cots
- open-r1/ioi-2024-model-solutions

reacted to BrigitteTousi's post with 🤗 15 days ago

Post

3702

Regardless of X being down or not, so glad I can rely on HF Posts for AI news ❤️🤗

1 reply

·

reacted to Smooke's post with 👍 16 days ago

Post

1859

reacted to JingzeShi's post with 🚀❤️ 17 days ago

Post

4679

We distill a more accurate and concise dataset from DeepSeek R1, and also provide a distillation pipeline code repository.🤗

Dataset: SmallDoge/SmallThoughts
Code: https://github.com/SmallDoges/small-thoughts

reacted to BlinkDL's post with 🔥 17 days ago

Post

5663

RWKV-7 "Goose" 0.4B trained w/ ctx4k automatically extrapolates to ctx32k+, and perfectly solves NIAH ctx16k 🤯 100% RNN and attention-free. Only trained on the Pile. No finetuning. Replicable training runs. tested by our community: https://github.com/Jellyfish042/LongMamba

reacted to fdaudens's post with 🤗 18 days ago

Post

5727

Honored to be named among their 12 pioneers and power players in the news industry in the 2025 Tech Trends Report from Future Today Strategy Group.

Incredible group to be part of - each person is doing groundbreaking work at the intersection of AI and journalism. Worth following them all: they're consistently sharing practical insights on building the future of news.

Take the time to read this report, it's packed with insights as always. The news & information section's #1 insight hits hard: "The most substantive economic impact of AI to date has been licensing payouts for a handful of big publishers. The competition will start shifting in the year ahead to separate AI 'haves' that have positioned themselves to grow from the 'have-nots.'"

This AI-driven divide is something I've been really concerned about. Now is the time to build more than ever!

👉 Full report here: https://ftsg.com/wp-content/uploads/2025/03/FTSG_2025_TR_FINAL_LINKED.pdf

2 replies

·

reacted to as-cle-bert's post with 👍 20 days ago

Post

2706

I just released a fully automated evaluation framework for your RAG applications!📈

GitHub 👉 https://github.com/AstraBert/diRAGnosis
PyPi 👉 https://pypi.org/project/diragnosis/

It's called 𝐝𝐢𝐑𝐀𝐆𝐧𝐨𝐬𝐢𝐬 and is a lightweight framework that helps you 𝗱𝗶𝗮𝗴𝗻𝗼𝘀𝗲 𝘁𝗵𝗲 𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 𝗼𝗳 𝗟𝗟𝗠𝘀 𝗮𝗻𝗱 𝗿𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 𝗺𝗼𝗱𝗲𝗹𝘀 𝗶𝗻 𝗥𝗔𝗚 𝗮𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀.

You can launch it as an application locally (it's Docker-ready!🐋) or, if you want more flexibility, you can integrate it in your code as a python package📦

The workflow is simple:
🧠 You choose your favorite LLM provider and model (supported, for now, are Mistral AI, Groq, Anthropic, OpenAI and Cohere)
🧠 You pick the embedding models provider and the embedding model you prefer (supported, for now, are Mistral AI, Hugging Face, Cohere and OpenAI)
📄 You prepare and provide your documents
⚙️ Documents are ingested into a Qdrant vector database and transformed into a synthetic question dataset with the help of LlamaIndex
📊 The LLM is evaluated for the faithfulness and relevancy of its retrieval-augmented answer to the questions
📊 The embedding model is evaluated for hit rate and mean reciprocal ranking (MRR) of the retrieved documents

And the cool thing is that all of this is 𝗶𝗻𝘁𝘂𝗶𝘁𝗶𝘃𝗲 𝗮𝗻𝗱 𝗰𝗼𝗺𝗽𝗹𝗲𝘁𝗲𝗹𝘆 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲𝗱: you plug it in, and it works!🔌⚡

Even cooler? This is all built on top of LlamaIndex and its integrations: no need for tons of dependencies or fancy workarounds🦙
And if you're a UI lover, Gradio and FastAPI are there to provide you a seamless backend-to-frontend experience🕶️

So now it's your turn: you can either get diRAGnosis from GitHub 👉 https://github.com/AstraBert/diRAGnosis
or just run a quick and painless:

uv pip install diragnosis

To get the package installed (lightning-fast) in your environment🏃‍♀️

Have fun and feel free to leave feedback and feature/integrations requests on GitHub issues✨

reacted to albertvillanova's post with 🔥 21 days ago

Post

3848

🚀 Big news for AI agents! With the latest release of smolagents, you can now securely execute Python code in sandboxed Docker or E2B environments. 🦾🔒

Here's why this is a game-changer for agent-based systems: 🧵👇

1️⃣ Security First 🔐
Running AI agents in unrestricted Python environments is risky! With sandboxing, your agents are isolated, preventing unintended file access, network abuse, or system modifications.

2️⃣ Deterministic & Reproducible Runs 📦
By running agents in containerized environments, you ensure that every execution happens in a controlled and predictable setting—no more environment mismatches or dependency issues!

3️⃣ Resource Control & Limits 🚦
Docker and E2B allow you to enforce CPU, memory, and execution time limits, so rogue or inefficient agents don’t spiral out of control.

4️⃣ Safer Code Execution in Production 🏭
Deploy AI agents confidently, knowing that any generated code runs in an ephemeral, isolated environment, protecting your host machine and infrastructure.

5️⃣ Easy to Integrate 🛠️
With smolagents, you can simply configure your agent to use Docker or E2B as its execution backend—no need for complex security setups!

6️⃣ Perfect for Autonomous AI Agents 🤖
If your AI agents generate and execute code dynamically, this is a must-have to avoid security pitfalls while enabling advanced automation.

⚡ Get started now: https://github.com/huggingface/smolagents

What will you build with smolagents? Let us know! 🚀💡

Nishith Jain

AI & ML interests

Recent Activity

Organizations

KingNish's activity