Downloads · 30 days
10
14% of all-time downloads
qwen3.6-27b-agentic-extraction-sft-merged
Koalacrown/qwen3.6-27b-agentic-extraction-sft-merged
qwen3.6-27b-agentic-extraction-sft-merged is a image-text-to-text model from Koalacrown. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
74
Public
Parameters
27.8B
55.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors55.6 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_5
- Access
- Public
- Created
- Jun 30, 2026
- Updated
- Jul 1, 2026
- SHA
- d0025e5c
Try a prompt
Base models
Model card
From the Hugging Face model README
qwen3.6-27b-agentic-extraction-sft-merged
Merged bf16 checkpoint.
Lineage
Qwen/Qwen3.6-27B (base, Qwen3_5ForConditionalGeneration)
└─ SFT LoRA → Koalacrown/qwen3.6-27b-agentic-extraction-sft-lora (trained on Tinker, run 7038c901)
└─ merge (build_hf_model) → this repo
- Base:
Qwen/Qwen3.6-27B - Adapter:
Koalacrown/qwen3.6-27b-agentic-extraction-sft-lora - Merge tool:
tinker_cookbook.weights.build_hf_model(LoRA deltas applied, bf16)
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_5
- License
- apache-2.0
- Languages
- en
- Created
- Jun 30, 2026
- Updated
- Jul 1, 2026