Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
TVP-SFTPoint-Qwen2VL-2B – AI Model by yunfengwang | AlphaNeural AI
You can deploy this model and start earning money today!
yunfengwang
/
TVP-SFTPoint-Qwen2VL-2B
like
0
peft
safetensors
visual-primitives
maze
path-tracing
lora
qwen2-vl
Qwen/Qwen2-VL-2B-Instruct
adapter
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
TVP-SFTPoint-Qwen2VL-2B
Point expert LoRA adapter for
Thinking with Visual Primitives
.
Stage 2: Specialized SFT (Point Expert)
— Maze navigation and path tracing with
<|point|>
tokens.
Base model
: Qwen/Qwen2-VL-2B-Instruct
LoRA
: r=64, alpha=128
Training data
: 5K maze + 3K path tracing samples
See the
project repo
for full instructions.
