SFT-trained step-level critic (Qwen3-8B) for code agents on SWE-bench Verified. Companion to https://github.com/shubhamrgandhi/critic-training
Shubham Gandhi
shubhamrgandhi
·
AI & ML interests
AI4Code
Recent Activity
updated a model 16 days ago
code-critic-model/Qwen3-4B-Critic-SFT-DPO updated a model 16 days ago
code-critic-model/Qwen3-4B-Critic-SFT commentedon a paper 21 days ago
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent TrainingOrganizations
models 14
shubhamrgandhi/Qwen3-4B-DPO-prm-pairs
Text Generation • 4B • Updated • 127
shubhamrgandhi/qwen3_5-4b-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only
Image-Text-to-Text • 5B • Updated • 8
shubhamrgandhi/qwen3_5-4b-full-sft-prm-r2egym-swebench-instructions-k5-cwm-plus-qwen
Image-Text-to-Text • 5B • Updated • 9
shubhamrgandhi/qwen3_5-9b-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only
Image-Text-to-Text • 9B • Updated • 5 • 1
shubhamrgandhi/qwen3_5-9b-full-sft-prm-r2egym-swebench-instructions-k5-cwm-plus-qwen
Image-Text-to-Text • 9B • Updated • 20
shubhamrgandhi/qwen3-8b-full-sft-prm-r2egym-swebench-k5-opus-distill-32k-lr5e6-multiturn
Text Generation • 1B • Updated • 24
shubhamrgandhi/qwen3-8b-full-sft-prm-r2egym-k5-opus-distill-32k-lr5e6-multiturn
Text Generation • 1B • Updated • 9
shubhamrgandhi/qwen3-8b-full-sft-prm-r2egym-instructions-k10-opus-distill-32k-lr5e6-multiturn
Updated
shubhamrgandhi/qwen3-8b-full-sft-prm-r2egym-instructions-k10-opus-distill-32k-lr5e6-flattened
Text Generation • 1B • Updated • 14
shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6-multiturn
Text Generation • 1B • Updated • 19
datasets 0
None public yet