Downloads · 30 days
6
13% of all-time downloads
hhhhwhit/lrat-qwen3-0.6b-retriever-utility-v2-20260803
lrat-qwen3-0.6b-retriever-utility-v2-20260803 is a feature extraction model from hhhhwhit. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as apache-2.0.
This retriever is trained from the released LRAT trajectory positives using supervision aligned with the information available to the retriever:
Downloads · 30 days
6
13% of all-time downloads
All-time downloads
48
Public
Parameters
596M
1.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.2 GB · 99%
From the Hugging Face model README
This retriever is trained from the released LRAT trajectory positives using supervision aligned with the information available to the retriever:
(web search query, document) pair from 0 through 4 for
standalone retrieval utility using Qwen3.5-4B.The utility judge does not use the agent's prior knowledge, visited-document history, post-browse reasoning, next action, or distance to the final task answer. In particular, a document is not downweighted merely because an agent had already observed the information.
Utility scores map to raw weights {0: 0.50, 1: 0.75, 2: 1.00, 3: 1.50, 4: 2.00}. Raw weights are divided by their global dataset mean. Training uses
weighted InfoNCE, sum_i(w_i * loss_i) / sum_i(w_i), with no pairwise loss or
reasoning-length weight.
Qwen/Qwen3-Embedding-0.6BYuqi-Zhou/LRAT-Train1e-60.10.02Query instruction:
Instruct: Given a web search query, retrieve relevant passages that answer the query
Query:{query}
The repository contains a full Transformers checkpoint and tokenizer files.