Downloads · 30 days
10
28% of all-time downloads
jatshi/EvidenceAgent-MM-Qwen3-1.7B-Agentic-GRPO-v3
EvidenceAgent-MM-Qwen3-1.7B-Agentic-GRPO-v3 is a text generation model from jatshi. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This is the compact PEFT export from the EvidenceAgent-MM v3 single-RTX-4090 engineering run. It targets evidence search, claim verification, citation-aware answers, clarification and abstention in a synthetic hard-ca…
Downloads · 30 days
10
28% of all-time downloads
All-time downloads
36
Public
Repo size
34.9 MB
Likes
0
Public
Click a slice to open those files.
.safetensors34.9 MB · 100%
From the Hugging Face model README
This is the compact PEFT export from the EvidenceAgent-MM v3 single-RTX-4090 engineering run. It targets evidence search, claim verification, citation-aware answers, clarification and abstention in a synthetic hard-case agent environment.
Qwen/Qwen3-1.7BThe step-50 actor, optimizer, RNG and data checkpoint were saved successfully. The subsequent post-save FSDP-to-vLLM weight synchronization OOMed by 194 MiB on the 24 GB GPU. The adapter therefore represents the saved step-50 actor, but the run did not perform a separate final evaluation after that failure. This is an engineering validation artifact, not a claim of production accuracy or medical safety.
See export_manifest.json and load_validation.json for machine-readable evidence.
The complete implementation and failure diary are in
EvidenceAgent-MM.
from peft import PeftModel
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B")
model = PeftModel.from_pretrained(
base,
"jatshi/EvidenceAgent-MM-Qwen3-1.7B-Agentic-GRPO-v3",
)