Gemma 4 Technical Report
Paper • 2607.02770 • Published • 76
AI & ML interests
Hackathon de PLN en español open-source y enfocado a los Objetivos de Desarrollo Sostenible de la ONU. Organizado por Somos NLP y patrocinado por Platzi, Paperspace y Hugging Face.
osanseviero
authored a
paper about 1 month ago
osanseviero
submitted a
paper to Daily Papers about 1 month ago
albertvillanova
posted an update about 1 month ago
Post
3690
🎉 KTO is now part of the stable TRL API
As of Promote KTO to stable API, KTOTrainer and KTOConfig have graduated from trl.experimental to the stable trl API. https://github.com/huggingface/trl/pull/6175
This one closes out a long road. Over the past 6+ months, the "Align KTO with DPO" effort landed ~90 PRs methodically bringing KTO up to the standard we hold for stable trainers, one carefully-scoped change at a time:
- Feature parity with DPO: full VLM support (incl. multi-image), sync_ref_model, PEFT + Liger, ZeRO-3 + PEFT dtype fix, pad_to_multiple_of, activation offloading, IterableDataset and dict eval_dataset, remove_unused_columns, and reference-logprob precomputation at init.
- Consistency with DPO: aligned method order and signatures, tokenization, _prepare_dataset, PEFT handling, ref-model preparation for distributed training, and config layout — plus a new DataCollatorForKTO and output format. Metrics moved into _compute_loss and simplified to direct averages via the shared _metrics attribute.
- Removing legacy baggage: dropped encoder-decoder support, BOS/EOS handling, null_ref_context, generate_during_eval, model_init, preprocess_logits_for_metrics, model/ref adapter names, and several dead config knobs.
- Coverage: a full test suite mirroring DPO, text collator tests, VLM tests, and slow tests.
- The promotion itself: the experimental → stable move (#6175) and shim cleanup (#6287), handled so downstream users get a clean deprecation path.
Honestly, this has been one of the more complex tasks I've taken on since joining the team, not because any single change was hard, but because it demanded sustained consistency across a ~2,000-line trainer, with every branch, comment, and edge case kept in lockstep with DPO.
Huge thanks to everyone who reviewed along the way (especially @qgallouedec ), the incremental review cadence is exactly what kept this maintainable.
KTO now sits on equal footing with our other flagship trainers. 🚀
As of Promote KTO to stable API, KTOTrainer and KTOConfig have graduated from trl.experimental to the stable trl API. https://github.com/huggingface/trl/pull/6175
This one closes out a long road. Over the past 6+ months, the "Align KTO with DPO" effort landed ~90 PRs methodically bringing KTO up to the standard we hold for stable trainers, one carefully-scoped change at a time:
- Feature parity with DPO: full VLM support (incl. multi-image), sync_ref_model, PEFT + Liger, ZeRO-3 + PEFT dtype fix, pad_to_multiple_of, activation offloading, IterableDataset and dict eval_dataset, remove_unused_columns, and reference-logprob precomputation at init.
- Consistency with DPO: aligned method order and signatures, tokenization, _prepare_dataset, PEFT handling, ref-model preparation for distributed training, and config layout — plus a new DataCollatorForKTO and output format. Metrics moved into _compute_loss and simplified to direct averages via the shared _metrics attribute.
- Removing legacy baggage: dropped encoder-decoder support, BOS/EOS handling, null_ref_context, generate_during_eval, model_init, preprocess_logits_for_metrics, model/ref adapter names, and several dead config knobs.
- Coverage: a full test suite mirroring DPO, text collator tests, VLM tests, and slow tests.
- The promotion itself: the experimental → stable move (#6175) and shim cleanup (#6287), handled so downstream users get a clean deprecation path.
Honestly, this has been one of the more complex tasks I've taken on since joining the team, not because any single change was hard, but because it demanded sustained consistency across a ~2,000-line trainer, with every branch, comment, and edge case kept in lockstep with DPO.
Huge thanks to everyone who reviewed along the way (especially @qgallouedec ), the incremental review cadence is exactly what kept this maintainable.
KTO now sits on equal footing with our other flagship trainers. 🚀
- 2 replies
haritzpuerto
authored a
paper 2 months ago
haritzpuerto
submitted a
paper to Daily Papers 2 months ago
espejelomar
posted an update 3 months ago
Post
4750
Sharing WorldForge with @abdelstark
It's an open-source Python project for evaluating and replaying robotics and world-model workflows.
The useful part is not only calling a model. WorldForge records the run, validates action shapes, translates outputs into actions, and keeps replay artifacts you can inspect later.
The current demo uses LeRobot + LeWorldModel on PushT through the official loader:
The harness also has replay-only paths for Cosmos-Policy and GR00T-style outputs, so you can inspect the provider contract from saved artifacts without keeping a GPU server online.
Try it:
Repo: https://github.com/AbdelStark/worldforge
Docs: https://abdelstark.github.io/worldforge/
Pre-1.0, MIT, and actively looking for contributors. Good areas:
- robotics provider adapters
- replay artifacts
- eval flows
- docs & first-run demos
Good first issues: https://github.com/AbdelStark/worldforge/contribute
If you're building robot policy evals or model adapters, would love a PR — or an issue describing what's missing.
It's an open-source Python project for evaluating and replaying robotics and world-model workflows.
The useful part is not only calling a model. WorldForge records the run, validates action shapes, translates outputs into actions, and keeps replay artifacts you can inspect later.
The current demo uses LeRobot + LeWorldModel on PushT through the official loader:
stable_worldmodel.policy.AutoCostModel("pusht/lewm")The harness also has replay-only paths for Cosmos-Policy and GR00T-style outputs, so you can inspect the provider contract from saved artifacts without keeping a GPU server online.
Try it:
pip install worldforge-aiuv run --extra harness worldforge-harness --flow robotics-compareRepo: https://github.com/AbdelStark/worldforge
Docs: https://abdelstark.github.io/worldforge/
Pre-1.0, MIT, and actively looking for contributors. Good areas:
- robotics provider adapters
- replay artifacts
- eval flows
- docs & first-run demos
Good first issues: https://github.com/AbdelStark/worldforge/contribute
If you're building robot policy evals or model adapters, would love a PR — or an issue describing what's missing.
haritzpuerto
authored a
paper 5 months ago
albertvillanova
posted an update 5 months ago
Post
3051
🚀 TRL v0.29.0 introduces trl-training: an agent-native training skill.
This makes the TRL CLI a structured, agent-readable capability, allowing AI agents to reliably execute training workflows such as:
- Supervised Fine-Tuning (SFT)
- Direct Preference Optimization (DPO)
- Group Relative Policy Optimization (GRPO)
We’re excited to see what the community builds on top of this.
If you’re working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! 🤗
The future of ML tooling is agent-native.
🔗 https://github.com/huggingface/trl/releases/tag/v0.29.0
This makes the TRL CLI a structured, agent-readable capability, allowing AI agents to reliably execute training workflows such as:
- Supervised Fine-Tuning (SFT)
- Direct Preference Optimization (DPO)
- Group Relative Policy Optimization (GRPO)
We’re excited to see what the community builds on top of this.
If you’re working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! 🤗
The future of ML tooling is agent-native.
🔗 https://github.com/huggingface/trl/releases/tag/v0.29.0
albertvillanova
posted an update 6 months ago
Post
2044
5 years already working in democratizing AI 🤗
Grateful to be part of such an awesome team making it happen every day.
Grateful to be part of such an awesome team making it happen every day.
Post
377
Last week, 
zai-org dropped zai-org/GLM-4.7-Flash. Now, we bring it to Microsoft Foundry!
- 🏆 30B-A3B MoE, the strongest model in the 30B class. It excels at coding tasks, agentic workflows and reasoning.
- 🤏🏻 Lighter version of his 358B big brother, balancing performance and efficiency.
Not light enough for you? We are also adding
unsloth unsloth/GLM-4.7-Flash-GGUF to the catalog, with GPU and CPU support powered by llama.cpp 🔥
Go join the hype and deploy them from the Hugging Face collection on Microsoft Foundry!
- 🏆 30B-A3B MoE, the strongest model in the 30B class. It excels at coding tasks, agentic workflows and reasoning.
- 🤏🏻 Lighter version of his 358B big brother, balancing performance and efficiency.
Not light enough for you? We are also adding
Go join the hype and deploy them from the Hugging Face collection on Microsoft Foundry!
- 2 replies
osanseviero
authored a
paper 11 months ago
albertvillanova
posted an update 12 months ago
Post
4643
Latest smolagents release supports GPT-5: build agents that think, plan, and act.
⚡ Upgrade now and put GPT-5 to work!
⚡ Upgrade now and put GPT-5 to work!
- 1 reply
albertvillanova
posted an update 12 months ago
Post
736
🚀 smolagents v1.21.0 is here!
Now with improved safety in the local Python executor: dunder calls are blocked!
⚠️ Still, not fully isolated: for untrusted code, use a remote executor instead: Docker, E2B, Wasm.
✨ Many bug fixes: more reliable code.
👉 https://github.com/huggingface/smolagents/releases/tag/v1.21.0
Now with improved safety in the local Python executor: dunder calls are blocked!
⚠️ Still, not fully isolated: for untrusted code, use a remote executor instead: Docker, E2B, Wasm.
✨ Many bug fixes: more reliable code.
👉 https://github.com/huggingface/smolagents/releases/tag/v1.21.0
haritzpuerto
authored 2
papers about 1 year ago
albertvillanova
posted an update about 1 year ago
Post
855
🚀 New in smolagents v1.20.0: Remote Python Execution via WebAssembly (Wasm)
We've just merged a major new capability into the smolagents framework: the CodeAgent can now execute Python code remotely in a secure, sandboxed WebAssembly environment!
🔧 Powered by Pyodide and Deno, this new WasmExecutor lets your agent-generated Python code run safely: without relying on Docker or local execution.
Why this matters:
✅ Isolated execution = no host access
✅ No need for Python on the user's machine
✅ Safer evaluation of arbitrary code
✅ Compatible with serverless / edge agent workloads
✅ Ideal for constrained or untrusted environments
This is just the beginning: a focused initial implementation with known limitations. A solid MVP designed for secure, sandboxed use cases. 💡
💡 We're inviting the open-source community to help evolve this executor:
• Tackle more advanced Python features
• Expand compatibility
• Add test coverage
• Shape the next-gen secure agent runtime
🔗 Check out the PR: https://github.com/huggingface/smolagents/pull/1261
Let's reimagine what agent-driven Python execution can look like: remote-first, wasm-secure, and community-built.
This feature is live in smolagents v1.20.0!
Try it out.
Break things. Extend it. Give us feedback.
Let's build safer, smarter agents; together 🧠⚙️
👉 https://github.com/huggingface/smolagents/releases/tag/v1.20.0
#smolagents #WebAssembly #Python #AIagents #Pyodide #Deno #OpenSource #HuggingFace #AgenticAI
We've just merged a major new capability into the smolagents framework: the CodeAgent can now execute Python code remotely in a secure, sandboxed WebAssembly environment!
🔧 Powered by Pyodide and Deno, this new WasmExecutor lets your agent-generated Python code run safely: without relying on Docker or local execution.
Why this matters:
✅ Isolated execution = no host access
✅ No need for Python on the user's machine
✅ Safer evaluation of arbitrary code
✅ Compatible with serverless / edge agent workloads
✅ Ideal for constrained or untrusted environments
This is just the beginning: a focused initial implementation with known limitations. A solid MVP designed for secure, sandboxed use cases. 💡
💡 We're inviting the open-source community to help evolve this executor:
• Tackle more advanced Python features
• Expand compatibility
• Add test coverage
• Shape the next-gen secure agent runtime
🔗 Check out the PR: https://github.com/huggingface/smolagents/pull/1261
Let's reimagine what agent-driven Python execution can look like: remote-first, wasm-secure, and community-built.
This feature is live in smolagents v1.20.0!
Try it out.
Break things. Extend it. Give us feedback.
Let's build safer, smarter agents; together 🧠⚙️
👉 https://github.com/huggingface/smolagents/releases/tag/v1.20.0
#smolagents #WebAssembly #Python #AIagents #Pyodide #Deno #OpenSource #HuggingFace #AgenticAI
not working
1
#1 opened about 1 year ago
by 
andresadmim
update sdk
#3 opened about 1 year ago
by 
pcuenq
update gradio
#2 opened about 1 year ago
by pcuenq
albertvillanova
posted an update about 1 year ago
Post
1889
🚀 SmolAgents v1.19.0 is live!
This release brings major improvements to agent flexibility, UI usability, streaming architecture, and developer experience: making it easier than ever to build smart, interactive AI agents. Here's what's new:
🔧 Agent Upgrades
- Support for managed agents in ToolCallingAgent
- Context manager support for cleaner agent lifecycle handling
- Output formatting now uses XML tags for consistency
🖥️ UI Enhancements
- GradioUI now supports reset_agent_memory: perfect for fresh starts in dev & demos.
🔄 Streaming Refactor
- Streaming event aggregation moved off the Model class
- ➡️ Better architecture & maintainability
📦 Output Tracking
- CodeAgent outputs are now stored in ActionStep
- ✅ More visibility and structure to agent decisions
🐛 Bug Fixes
- Smarter planning logic
- Cleaner Docker logs
- Better prompt formatting for additional_args
- Safer internal functions and final answer matching
📚 Docs Improvements
- Added quickstart examples with tool usage
- One-click Colab launch buttons
- Expanded reference docs (AgentMemory, GradioUI docstrings)
- Fixed broken links and migrated to .md format
🔗 Full release notes:
https://github.com/huggingface/smolagents/releases/tag/v1.19.0
💬 Try it out, explore the new features, and let us know what you build!
#smolagents #opensource #AIagents #LLM #HuggingFace
This release brings major improvements to agent flexibility, UI usability, streaming architecture, and developer experience: making it easier than ever to build smart, interactive AI agents. Here's what's new:
🔧 Agent Upgrades
- Support for managed agents in ToolCallingAgent
- Context manager support for cleaner agent lifecycle handling
- Output formatting now uses XML tags for consistency
🖥️ UI Enhancements
- GradioUI now supports reset_agent_memory: perfect for fresh starts in dev & demos.
🔄 Streaming Refactor
- Streaming event aggregation moved off the Model class
- ➡️ Better architecture & maintainability
📦 Output Tracking
- CodeAgent outputs are now stored in ActionStep
- ✅ More visibility and structure to agent decisions
🐛 Bug Fixes
- Smarter planning logic
- Cleaner Docker logs
- Better prompt formatting for additional_args
- Safer internal functions and final answer matching
📚 Docs Improvements
- Added quickstart examples with tool usage
- One-click Colab launch buttons
- Expanded reference docs (AgentMemory, GradioUI docstrings)
- Fixed broken links and migrated to .md format
🔗 Full release notes:
https://github.com/huggingface/smolagents/releases/tag/v1.19.0
💬 Try it out, explore the new features, and let us know what you build!
#smolagents #opensource #AIagents #LLM #HuggingFace