Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mllm-mmr1-gt-gemma3-12b – AI Model by q1716523669 | AlphaNeural AI
You can deploy this model and start earning money today!
q1716523669
/
mllm-mmr1-gt-gemma3-12b
like
0
safetensors
gemma3
co-rl
mllm
mmr1
reasoning
image-text-to-text
conversational
google/gemma-3-12b-it
finetune
gemma
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
q1716523669/mllm-mmr1-gt-gemma3-12b
Base: google/gemma-3-12b-it
Method: GT-GRPO (ground-truth labels)
Dataset: mmr1 (~8k), 1 epoch
Checkpoint: best (best_model)
4-bench avg: **47.4 **
best repo:
q1716523669/mllm-mmr1-gt-gemma3-12b
· endpoint repo:
q1716523669/mllm-mmr1-gt-gemma3-12b-endpoint
eval: prompt=answer, greedy T=0, mathruler; see results.csv in run.