arxiv:2307.15343
Logesh Kumar umapathi
infinitylogesh
AI & ML interests
NLP - Healthcare , Information retrieval , Open domain question answering.
Recent Activity
updated
a dataset
about 16 hours ago
infinitylogesh/book_dataset_no_mem_token_gte_largev1_5_M512_C1024_1B
published
a dataset
about 16 hours ago
infinitylogesh/book_dataset_no_mem_token_gte_largev1_5_M512_C1024_1B
updated
a model
5 days ago
infinitylogesh/qwen3_1_7b_base_srt_grpo_math_12k_single_stage_fullfinetuning_ckpt50
Organizations
models
14
infinitylogesh/qwen3_1_7b_base_srt_grpo_math_12k_single_stage_fullfinetuning_ckpt50
2B
•
Updated
•
8
infinitylogesh/qwen3_1_7b_base_srt_grpo_math_12k_single_stage_fullfinetuning_ckpt100
2B
•
Updated
•
10
infinitylogesh/qwen3_1_7b_base_srt_grpo_math_12k_single_stage_rollout_16_fullfinetuning_merged
2B
•
Updated
•
8
infinitylogesh/Qwen3-1.7B-GRPO-SRT-Math-12k-Single-Stage-Rollout-16-Full-Finetuning
2B
•
Updated
•
8
infinitylogesh/Qwen3-1.7B-GRPO-SRT-Math-12k-Stage-2
Text Generation
•
2B
•
Updated
•
29
infinitylogesh/Qwen3-1.7B-GRPO-SRT-Math-12k-Stage-1
Text Generation
•
2B
•
Updated
•
11.6k
infinitylogesh/Qwen2.5-1.5B-GRPO-SRT-Math-12k-Stage-0_lora
Updated
infinitylogesh/Qwen2.5-1.5B-GRPO-SRT-Math-12k-Stage-0
Text Generation
•
2B
•
Updated
•
22
infinitylogesh/Qwen3-1.7B-GRPO-SRT-Math-12k-Stage-0
Text Generation
•
2B
•
Updated
•
16.5k
infinitylogesh/infinitylogesh
Robotics
•
Updated
•
8
datasets
6
infinitylogesh/book_dataset_no_mem_token_gte_largev1_5_M512_C1024_1B
Viewer
•
Updated
•
606k
infinitylogesh/math_12k_srt_single_stage
Viewer
•
Updated
•
12.5k
•
9
infinitylogesh/math_12k_srt_splits
Viewer
•
Updated
•
13.5k
•
17
infinitylogesh/eval_grab_toy_car_smolvla
Viewer
•
Updated
•
3.23k
•
61
infinitylogesh/eval_grab_toy_car_act
Viewer
•
Updated
•
1.2k
•
58
infinitylogesh/eval_desk_setup_record_1_cam_smolvla_2
Viewer
•
Updated
•
497
•
16