Downloads · 30 days
6
24% of all-time downloads
widget2code-qwen3.5-27b-size-tools-merged-bf16
Djanghao/widget2code-qwen3.5-27b-size-tools-merged-bf16
widget2code-qwen3.5-27b-size-tools-merged-bf16 is a image-text-to-text model from Djanghao. 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.
This repository contains full BF16 weights for a Widget2Code SFT model based on Qwen/Qwen3.5-27B. A rank-32 LoRA adapter (loraalpha=64) was merged into the base model with PEFT mergeandunload(safemerge=True).
All-time downloads
25
Public
Parameters
27.4B
54.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors54.7 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_5
- Access
- Public
- Created
- Aug 19, 2026
- Updated
- Aug 19, 2026
- SHA
- 77eae12f
Try a prompt
Base models
Model card
From the Hugging Face model README
Widget2Code Qwen3.5-27B SFT (merged BF16)
This repository contains full BF16 weights for a Widget2Code SFT model based
on Qwen/Qwen3.5-27B. A rank-32 LoRA adapter (lora_alpha=64) was merged into
the base model with PEFT merge_and_unload(safe_merge=True).
Artifact details
- Base model:
Qwen/Qwen3.5-27B - Format: Hugging Face Transformers safetensors
- Saved parameters: 27,356,728,560
- Weight dtype: BF16
- Adapter training dataset name:
widget2code_sft
merge_provenance.json records the base revision, adapter configuration,
adapter hashes, merge environment, and audited tensor inventory. The saved
weights contain no remaining LoRA tensors.
Usage
from transformers import AutoModelForImageTextToText, AutoProcessor
model_id = "Djanghao/widget2code-qwen3.5-27b-size-tools-merged-bf16"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
model_id,
dtype="auto",
device_map="auto",
)
Limitations
No standalone benchmark results are included in this model card. Users should evaluate the model on their target screenshot-to-code distribution before deployment.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Aug 19, 2026
- Updated
- Aug 19, 2026