Rajat Ghosh PRO
rghosh8
AI & ML interests
None yet
Recent Activity
updated a collection 1 day ago
GSM8k-GRPO updated a collection 1 day ago
GSM8k-GRPO updated a model 1 day ago
rghosh8/gsm8k-grpo-deepseek-r1-distill-qwen-1.5b-seed-1234-G-4_mergedOrganizations
models 199
rghosh8/gsm8k-grpo-deepseek-r1-distill-qwen-1.5b-seed-1234-G-4_merged
Text Generation • 2B • Updated
rghosh8/gsm8k-grpo-deepseek-r1-distill-qwen-1.5b-seed-1234-G-4
Text Generation • Updated
rghosh8/gsm8k-grpo-deepseek-r1-distill-qwen-1.5b-seed-1234-G-16_merged
Text Generation • 2B • Updated • 357
rghosh8/gsm8k-grpo-deepseek-r1-distill-qwen-1.5b-seed-1234-G-16
Text Generation • Updated • 24
rghosh8/SFT_baseline_deepseek-llm-7b-chat_opencoder_1234
Text Generation • 7B • Updated • 669
rghosh8/SFT_baseline_deepseek-llm-7b-chat_opencoder_3407
Text Generation • 7B • Updated • 652
rghosh8/SFT_baseline_deepseek-llm-7b-chat_opencoder_42
Text Generation • 7B • Updated • 350
rghosh8/SFT_baseline_Nemotron-Mini-4B-Instruct_opencoder_1234
Text Generation • 4B • Updated • 294
rghosh8/SFT_baseline_Nemotron-Mini-4B-Instruct_opencoder_3407
Text Generation • 4B • Updated • 398
rghosh8/SFT_baseline_Nemotron-Mini-4B-Instruct_opencoder_42
Text Generation • 4B • Updated • 252
datasets 14
rghosh8/deepseek-llm-7b-chat-opencoder-educational-instruct-seed-1234-G-4-log
Updated • 25
rghosh8/nemotron-mini-4b-instruct-opencoder-educational-instruct-seed-1234-G-4-log
Updated • 27
rghosh8/deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-1234-G-4-log
Updated • 31
rghosh8/deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-1234-G-8-log
Updated • 28
rghosh8/cr-bench-verified
Viewer • Updated • 174 • 68 • 1
rghosh8/nemotron-mini-4b-instruct-opencoder-educational-instruct-seed-1234-G-8-log
Updated • 26
rghosh8/deepseek-llm-7b-chat-opencoder-educational-instruct-seed-1234-G-8-log
Updated • 51
rghosh8/opencoder-grpo-deepseek-llm-7b-chat-seed-1234-G-8-log
Updated • 53
rghosh8/opencoder-grpo-deepseek-llm-7b-chat-seed-1234-G-4-log
Updated • 39
rghosh8/math-lighteval-processed
Viewer • Updated • 7.5k • 7