Downloads · 30 days
0
Pradheep1647/smollm2-135m-instruct-paper-preference-150k-v1-sft-dpo-lr5e-6-ep1-beta0-1-lora16a32-seq1024
smollm2-135m-instruct-paper-preference-150k-v1-sft-dpo-lr5e-6-ep1-beta0-1-lora16a32-seq1024 is a machine learning model from Pradheep1647. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for verl.
trained with verl for paper-query citation chunk grounding.
Downloads · 30 days
0
Access
Public
Updated Jun 9, 2026
Repo size
22.4 MB
Likes
0
Public
Click a slice to open those files.
.pt15 MB · 38%
From the Hugging Face model README
trained with verl for paper-query citation chunk grounding.
HuggingFaceTB/SmolLM2-135M-Instructpaperbd/paper_preference_150K-v1sft-dpo-lr5e-6-ep1-beta0.1-lora16a32-seq1024paperhoundthe dataset contains positive cited chunks, not the full arxiv paper haystack, so this model is trained to emit known supporting chunks for a paper/query pair.