johnlockejrr/yolo11_syr_synth
Updated
John Locke
johnlockejrr
AI & ML interests
OCR, HTR, ATR, NLP, AI
Recent Activity
liked a dataset about 2 hours ago
seemorg/books-ocr reacted to qgallouedec's post with 🚀 about 14 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 1 day ago
johnlockejrr/ICDAR2026-ret-meta-NFDOrganizations
johnlockejrr/pylaya_syr_synth
Updated
johnlockejrr/norhand-regions-lines
Updated
johnlockejrr/yolo_samaritan
Updated
johnlockejrr/medieval-manuscript-yolov11-seg
Object Detection • Updated
johnlockejrr/pylaia_catmus_medieval
Image-to-Text • Updated • 1
johnlockejrr/pylaia-heb_sam_v1
Image-to-Text • Updated
johnlockejrr/pylaia-mcdonald_v2
Image-to-Text • Updated
johnlockejrr/pylaia-ar-hand_v1
Image-to-Text • Updated
johnlockejrr/pylaia-samaritan_v1
Image-to-Text • Updated
johnlockejrr/trocr_syr_v1
61.6M • Updated • 4
johnlockejrr/syrnt_v2_20-epoch
Updated • 1
johnlockejrr/syrnt_v2_13-epoch
Updated • 1
johnlockejrr/syrnt_v2
Updated • 4
johnlockejrr/sbb_pixelwise_v1
Updated • 6
johnlockejrr/yolov8-samaritan-segmentation
Updated
johnlockejrr/doc_ufcn_samaritan_v2
Image Segmentation • Updated
johnlockejrr/doc_ufcn_samaritan_v1
Image Segmentation • Updated
johnlockejrr/doc-ufcn-samaritan
Image Segmentation • Updated
johnlockejrr/heBERT-finetuned-samaritan
Fill-Mask • 0.1B • Updated • 1
johnlockejrr/BEREL_2.0-sam-v3
Fill-Mask • 0.2B • Updated • 1