bpHigh/trackio-office-grpo-bucket
3.04 MB
Bhavish Pahwa
bpHigh
AI & ML interests
Hate Speech, Domain Identification, NER, Summarisation, Performance metrics for various NLP tasks
Recent Activity
new activity about 5 hours ago
reflection/Beam-1.0-501B-A23B:Build with Beam - $20K in prizes updated a dataset about 7 hours ago
bpHigh/FloodGate updated a Space about 7 hours ago
bpHigh/FloodGateOrganizations
Articles 2
Article
Building a cross-format office-document RL environment
Article
1
Teaching LLMs to Play Carrom: A Physics-Based RL Environment for Frontier Agents
spaces 10
Running on Zero
Agents
RL
1
FloodGate v1
🌊
Run the Army Corps' Cumberland dams through real 2025 floods
Running on Zero
Agents
RL
2
RailSimEnv v1
🚆
Dispatch trains on a real single-track Dutch line
Running
Agents
Amul AI x CeRAI evaluation
🐄
Evaluating Amul AI with CeRAI's AIEvaluationTool
Paused
RL
2
Office Document Task Environment
📊
Explore office document RL tasks and model performance
Sleeping
Agents
Trackio Office Grpo
🐠
Office Openenv environment training tracking space
Running
RL
1
Carrom RL Env
🎯
Play a physics‑based Carrom board game in your browser
models 16
bpHigh/glance-0.1
Updated • 1
bpHigh/qwen3b-office-grpo-from-base
Updated
bpHigh/qwen3b-office-grpo
Updated
bpHigh/qwen3b-office-sft-kimi-long
Updated
bpHigh/qwen3b-office-sft-kimi
Updated
bpHigh/gstar_assignment_2_prompt_modified_grpo_max_tokens_256_steps_120
2B • Updated • 5
bpHigh/gstar_assignment_2_baseline_max_tokens_256_steps_80
2B • Updated • 7
bpHigh/CE_TOTAL_TRANSLATED_EXCEPT_MARATHI_SEMREL
Text Classification • 0.3B • Updated • 11
bpHigh/CE_TOTAL_TRANSLATED_AUGMENTED_SEMREL
Text Classification • 0.3B • Updated • 5
bpHigh/CE_MA_TE_AUGMENTED_SEMREL
Text Classification • 0.3B • Updated • 8
datasets 11
bpHigh/FloodGate
RL Environment • Updated • 24 • 190
bpHigh/finance-desk
RL Environment • Updated • 276 • 211
bpHigh/railsim-arena
Preview • Updated • 113 • 1
bpHigh/BIRCO_Doris_Mae_Without_Task_Awareness
Updated • 18
bpHigh/BIRCO_Doris_Mae
Updated • 18
bpHigh/BIRCO_WhatsThatBook_Without_Task_Awareness
Viewer • Updated • 100 • 13
bpHigh/BIRCO_WhatsThatBook
Viewer • Updated • 100 • 22
bpHigh/BIRCO_ArguAna_Without_Task_Awareness
Viewer • Updated • 100 • 22
bpHigh/BIRCO_ArguAnu
Viewer • Updated • 100 • 29
bpHigh/iNLTK_Sanskrit_Shlokas_Dataset
Viewer • Updated • 479 • 419 • 2