Hiring 💼

Quentin Gallouédec PRO

qgallouedec

AI & ML interests

None yet

Recent Activity

posted an update about 4 hours ago

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: ```python 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

updated a dataset about 18 hours ago

hf-doc-build/doc-build

updated a bucket about 18 hours ago

hf-doc-build/doc

View all activity

Organizations

buckets 61

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