Shubham Gandhi

shubhamrgandhi's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article 1 day ago

view article

Article

Model Routing Is Simple. Until It Isn’t.

• 

ibm-research

•

9 days ago

• 56

updated a model 7 days ago

shubhamrgandhi/qwen3_5-4b-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only

Image-Text-to-Text • 5B • Updated 7 days ago • 21

published a model 7 days ago

shubhamrgandhi/qwen3_5-4b-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only

Image-Text-to-Text • 5B • Updated 7 days ago • 21

updated a model 8 days ago

shubhamrgandhi/qwen3_5-4b-full-sft-prm-r2egym-swebench-instructions-k5-cwm-plus-qwen

Image-Text-to-Text • 5B • Updated 8 days ago • 16

published a model 8 days ago

shubhamrgandhi/qwen3_5-4b-full-sft-prm-r2egym-swebench-instructions-k5-cwm-plus-qwen

Image-Text-to-Text • 5B • Updated 8 days ago • 16

updated a model 9 days ago

shubhamrgandhi/qwen3_5-9b-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only

Image-Text-to-Text • 9B • Updated 9 days ago • 17 • 1

published a model 9 days ago

shubhamrgandhi/qwen3_5-9b-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only

Image-Text-to-Text • 9B • Updated 9 days ago • 17 • 1

updated a model 9 days ago

shubhamrgandhi/qwen3_5-9b-full-sft-prm-r2egym-swebench-instructions-k5-cwm-plus-qwen

Image-Text-to-Text • 9B • Updated 9 days ago • 17

published a model 9 days ago

shubhamrgandhi/qwen3_5-9b-full-sft-prm-r2egym-swebench-instructions-k5-cwm-plus-qwen

Image-Text-to-Text • 9B • Updated 9 days ago • 17

published a model 13 days ago

shubhamrgandhi/qwen3-8b-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only

Updated 13 days ago

updated a model 13 days ago

shubhamrgandhi/qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only

Text Generation • 4B • Updated 13 days ago • 530

published a model 13 days ago

shubhamrgandhi/qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only

Text Generation • 4B • Updated 13 days ago • 530

updated a model 13 days ago

shubhamrgandhi/qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-cwm-plus-qwen

Text Generation • 4B • Updated 13 days ago • 230

published a model 14 days ago

shubhamrgandhi/qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-cwm-plus-qwen

Text Generation • 4B • Updated 13 days ago • 230

liked a Space about 1 month ago

Running

Featured

59

CUGA Apps

🚀

59

2 dozen real-life agents optimized for open models & stack

updated a collection about 2 months ago

Critic Training for Code Agents

Collection

SFT-trained step-level critic (Qwen3-8B) for code agents on SWE-bench Verified. Companion to https://github.com/shubhamrgandhi/critic-training • 6 items • Updated Jun 9

updated 2 models about 2 months ago

shubhamrgandhi/qwen3-8b-full-sft-prm-r2egym-swebench-k5

Text Generation • 1B • Updated Jun 9 • 4

shubhamrgandhi/qwen3-8b-full-sft-prm-r2egym-swebench-instructions-k5-cwm-plus-qwen

Text Generation • 1B • Updated Jun 9 • 3

published a model about 2 months ago

shubhamrgandhi/qwen3-8b-full-sft-prm-r2egym-swebench-k5

Text Generation • 1B • Updated Jun 9 • 4