Article
Running AI agents to automate outreach at scale
โข
13
Albert Villanova del Moral
albertvillanova
AI & ML interests
ML Engineer @ Hugging Face: Agents (Science)
Recent Activity
new activity 7 days ago
trl-internal-testing/tiny-Gemma3ForConditionalGeneration:Upload Gemma3ForConditionalGeneration new activity 7 days ago
trl-internal-testing/tiny-Gemma3ForConditionalGeneration:Upload Gemma3ForConditionalGeneration new activity 7 days ago
trl-internal-testing/tiny-Gemma3ForConditionalGeneration:Upload Gemma3ForConditionalGenerationOrganizations
Upload Gemma3ForConditionalGeneration
#10 opened 7 days ago
by 
albertvillanova
Upload Gemma3ForConditionalGeneration
#9 opened 7 days ago
by albertvillanova
Upload Gemma3ForConditionalGeneration
#8 opened 7 days ago
by albertvillanova
upvoted an article 9 days ago
reacted to qgallouedec's post with ๐ฅ๐ 10 days ago
Post
7879
TRL v1.3 ships day-one training support for Qwen 3.6 ๐
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 โ 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 โ 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
Upload GptOssForCausalLM
#2 opened 15 days ago
by albertvillanova
Upload GptOssForCausalLM
#1 opened 15 days ago
by albertvillanova
upvoted an article about 1 month ago
Article
TRL v1.0: Post-Training Library Built to Move with the Field
- +2
โข
51
updated a
dataset about 2 months ago
published a
dataset about 2 months ago
upvoted an article about 2 months ago
Article
Introducing Storage Buckets on the Hugging Face Hub
- +10
โข
194
published an article about 2 months ago
Article
Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries
- +7
โข
142
posted an update 2 months ago
Post
2571
๐ 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)
Weโre excited to see what the community builds on top of this.
If youโre working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! ๐ค
The future of ML tooling is agent-native.
๐ 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)
Weโre excited to see what the community builds on top of this.
If youโre working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! ๐ค
The future of ML tooling is agent-native.
๐ https://github.com/huggingface/trl/releases/tag/v0.29.0
Convert dataset to Parquet
1
#15 opened 3 months ago
by 
lhoestq
liked a
Space 3 months ago
posted an update 3 months ago
Post
1904
5 years already working in democratizing AI ๐ค
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.
Delete malformed and deprecated chat_template.json
#5 opened 3 months ago
by albertvillanova
Upload LlavaNextForConditionalGeneration
#4 opened 3 months ago
by albertvillanova
upvoted an article 3 months ago
Article
Gotchas in Tokenizer Behavior Every Developer Should Know
โข
72