AdithyaSK/async-grpo-harbor-dataagent-static-b6d9a4-bucket
70.4 MB
Adithya S K
AdithyaSK
AI & ML interests
None yet
Recent Activity
updated a collection about 6 hours ago
Data Agent updated a collection about 6 hours ago
Data Agent updated a collection about 6 hours ago
Data AgentOrganizations
spaces 40
Running
The ultimate guide to multi-harness RL
🔀
Training and evals together across many agent harnesses
Running
Async Grpo Harbor Dataagent Static B6d9a4
🎯
View and manage tracked data with an interactive dashboard
Running
Harbor Run Viewer
🔭
Explore model benchmark results with interactive heatmaps
Sleeping
Agents
Harbor Dataagent Trackio
🎯
Show interactive tracking dashboard
Running
RL
Scaling RL for LLMs — Slides
📈
Scaling RL for LLMs — AMD AI Dev Day slides
Sleeping
RL
Harbor
⚓
Run coding agent on Harbor tasks and save token logs
models 45
AdithyaSK/data-agent-4b-normal-best
Text Generation • 5B • Updated • 12
AdithyaSK/data-agent-4b-normal-final
Text Generation • 5B • Updated • 15
AdithyaSK/data-agent-2b-curriculum-best
Text Generation • 3B • Updated • 12
AdithyaSK/data-agent-2b-curriculum-final
Text Generation • 3B • Updated • 12
AdithyaSK/data-agent-2b-normal-best
Text Generation • 3B • Updated • 12
AdithyaSK/data-agent-2b-normal-final
Text Generation • 3B • Updated • 15
AdithyaSK/qwen3.5-latex-ocr-grpo
Image-Text-to-Text • 5B • Updated • 6
AdithyaSK/cursor-detection-yolov8n
Updated
AdithyaSK/bunny-llama3-1b-latex-ocr-main
Updated
AdithyaSK/gemma-3n-e2b-ft
5B • Updated • 8
datasets 57
AdithyaSK/data_agent_harbor_train_sft
Viewer • Updated • 4.68k
AdithyaSK/data_agent
Viewer • Updated • 5.39k
AdithyaSK/data_agent_harbor_eval
Updated • 17
AdithyaSK/data_agent_harbor_test
Updated
AdithyaSK/data_agent_harbor_train
Updated
AdithyaSK/data_agent_rl_environment_eval
Updated • 549 • 3
AdithyaSK/data_agent_rl_environment_train_difficulty_ranked
Updated • 9.03k • 1
AdithyaSK/data_agent_rl_environment_train_multireward
Updated • 98 • 1
AdithyaSK/HF_ML_Bench_v0
Updated • 273
AdithyaSK/repo2rlenv-equivalence-tests
Updated • 496