Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
opscribe-captioner-ortho-tool-v3 – AI Model by rbryant19 | AlphaNeural AI
You can deploy this model and start earning money today!
rbryant19
/
opscribe-captioner-ortho-tool-v3
like
0
peft
safetensors
adapter
lora
transformers
orthopaedic-surgery
frame-captioning
image-text-to-text
conversational
Qwen/Qwen2.5-VL-72B-Instruct
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
opscribe-captioner-ortho-tool-v3
SVD task arithmetic merge for Qwen2.5-VL-72B-Instruct surgical frame captioning.
Adapter
Weight
Rank
Data
captioner_voiceover_v1
0.60
16
Surgeon-narrated ortho voiceover dataset — broad visual vocabulary
captioner_v2
0.40
32
Targeted v2 dataset (793 train) — priority-tool pass for mallet, reamer, Bovie, saw
Merged to rank 32 (alpha=32, scale=1.0) via efficient thin-SVD task arithmetic. v3 corrects v2 weight inversion: voiceover_v1 is now dominant (0.60) to preserve broad vocabulary.
Training Details
captioner_v2 best val_loss: 0.0963 (3 epochs)
Hardware: 4× NVIDIA H200, device_map=auto, bf16
LoRA targets: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
