Downloads · 30 days
5
17% of all-time downloads
emb-rag-qwen4b-relsft
Icey444/emb-rag-qwen4b-relsft
emb-rag-qwen4b-relsft is a reinforcement learning model from Icey444. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
LoRA adapter for Qwen/Qwen3-Embedding-4B — Relevance-SFT (direct; winner recipe).
All-time downloads
30
Public
Repo size
276 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors264 MB · 94%
At a glance
- Task
- Reinforcement Learning
- Library
- peft
- Access
- Public
- Created
- Jul 14, 2026
- Updated
- Jul 14, 2026
- SHA
- d5a828c9
Base models
Model card
From the Hugging Face model README
emb-rag-qwen4b-relsft
LoRA adapter for Qwen/Qwen3-Embedding-4B — Relevance-SFT (direct; winner recipe).
Trained on multi-hop MuSiQue; evaluated on MuSiQue (in-domain) + 2WikiMultiHopQA, HotpotQA, NQ, TriviaQA (OOD).
Indirect feedback = the reward is a frozen reader LLM's answer success (log p(gold answer | query, retrieved context)) — no passage-level relevance labels. Rel-SFT = the direct-supervision baseline (contrastive InfoNCE on gold passages).
Full results (retrieval R@k + downstream RAG accuracy) and training scripts: https://irisicy4.github.io/exp-record/projects/indirect-rag/
from peft import PeftModel
from transformers import AutoModel, AutoTokenizer
base = AutoModel.from_pretrained("Qwen/Qwen3-Embedding-4B")
model = PeftModel.from_pretrained(base, "Icey444/emb-rag-qwen4b-relsft").merge_and_unload()
tok = AutoTokenizer.from_pretrained("Icey444/emb-rag-qwen4b-relsft")
- Task
- Reinforcement Learning
- Library
- peft
- Created
- Jul 14, 2026
- Updated
- Jul 14, 2026