Bringing my ideas to life
Gagan Bhatia
gagan3012
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
14 days ago
Offline Reinforcement Learning for LLM Multi-Step Reasoning
authored
a paper
17 days ago
DateLogicQA: Benchmarking Temporal Biases in Large Language Models
Organizations
Collections
1
spaces
15
models
91
gagan3012/index_wikipedia_arabic
Updated
gagan3012/Qwen2-VL-2B-Instruct-LoRA-AR
Updated
•
3
gagan3012/Florence-2-FT-ArabicOCR
Text Generation
•
Updated
•
91
•
2
gagan3012/Mistral_arabic_dpo_agec_final_combined
Text Generation
•
Updated
•
20
gagan3012/ArMistral-GEC
Text Generation
•
Updated
•
23
gagan3012/tinyllama-20480
Text Generation
•
Updated
•
26
gagan3012/dpo-test
Text Generation
•
Updated
•
11
gagan3012/Multilingual-mistral-asian
Text Generation
•
Updated
•
16
gagan3012/Multilingual-mistral
Text Generation
•
Updated
•
804
•
2
gagan3012/MegaArabic
Text Generation
•
Updated
•
15
datasets
97
gagan3012/DateLogicQA
Viewer
•
Updated
•
190
•
21
gagan3012/TimeBench-event
Preview
•
Updated
•
7
gagan3012/TimeLLAMA-Eval
Viewer
•
Updated
•
1k
•
2
gagan3012/temporal_qa
Viewer
•
Updated
•
11k
•
2
gagan3012/skyworks_reward_model_prefs_v2
Viewer
•
Updated
•
77k
•
29
gagan3012/skyworks_reward_model_prefs
Viewer
•
Updated
•
100
•
30
gagan3012/helpsteer2-preference-v2
Viewer
•
Updated
•
9.13k
•
36
gagan3012/helpsteer2-preference
Viewer
•
Updated
•
9.13k
•
64
gagan3012/dpo-fix
Viewer
•
Updated
•
3.4k
•
48
gagan3012/multi-reward-bench
Viewer
•
Updated
•
2.99k
•
30