qgallouedec/huggingface-static-1b2b9a-bucket
358 kB
Quentin Gallouédec PRO
qgallouedec
AI & ML interests
None yet
Recent Activity
updated a bucket about 21 hours ago
hf-doc-build/doc-dev updated a dataset 1 day ago
hf-doc-build/doc-build updated a bucket 1 day ago
hf-doc-build/docOrganizations
Posts 4
Post
7548
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
Articles 14
Article
50
TRL v1.0: Post-Training Library Built to Move with the Field
spaces 87
pinned
Running
Diff Viewer
⚡
Compare two code files side‑by‑side
Running
Huggingface Static 1b2b9a
🚀
View interactive dashboards to monitor your data in real time
Running
Huggingface Static 041dff
🚀
View and manage your tracking dashboard
Running
Huggingface Static 8fedf1
🚀
Visualize your tracked data with an interactive dashboard
Running
Huggingface Static D98a4d
🚀
Explore your data with an interactive Trackio dashboard
Running
Huggingface Static Db0349
🚀
View your tracked data on an interactive dashboard
models 789
qgallouedec/Qwen3-0.6B-SFT-20251113165959
Text Generation • 0.6B • Updated • 292
qgallouedec/tiny-aya-global-SFT
Updated
qgallouedec/tiny-aya-global-tool-calling-SFT
Updated
qgallouedec/my-other-awesome-model
Text Generation • 0.5B • Updated • 12
qgallouedec/my-awesome-model
Text Generation • 0.5B • Updated • 13
qgallouedec/trainer_output
Text Generation • 0.5B • Updated • 10
qgallouedec/test_push_output_4
Text Classification • 87.5k • Updated • 6
qgallouedec/qwen2-0.5b-deepmath-grpo
Updated
qgallouedec/my-finetuned-model
0.8B • Updated • 1
qgallouedec/Qwen3-0.6B-SFT-20251113163732
Updated
datasets 85
qgallouedec/test-grpo-vlm-log-completions
Viewer • Updated • 435 • 136
qgallouedec/llama_star_formatted
Viewer • Updated • 7.21k • 7
qgallouedec/deepmath-completions-logs2
Viewer • Updated • 48 • 59
qgallouedec/deepmath-completions-logs
Viewer • Updated • 232 • 54 • 1
qgallouedec/Dolci-Think-DPO-7B
Viewer • Updated • 150k • 14
qgallouedec/biogrid_qa
Viewer • Updated • 59.4k • 278
qgallouedec/human_gene_interaction_qa_v2
Viewer • Updated • 79.2k • 10
qgallouedec/human_gene_interaction_qa
Viewer • Updated • 1.84M • 14
qgallouedec/biogrid
Viewer • Updated • 2.82M • 927
qgallouedec/trl-metrics
Viewer • Updated • 148k • 53 • 1