git
ask
hub
Privacy
Terms
Sign in with GitHub
clawgym/clawgym-agents
↗
Stars ·
31
Language ·
Python
Simplify and Visualize This Repo
Scan the safety of this repo
Self Host this repo
Check out more work of Developer: clawgym
Ask anything about this repo to start.
Walk me through the SFT folder of ClawGym-Agents and show what scripts run supervised fine-tuning
Pull the ClawGym-Task dataset from Hugging Face and write a Python loader that yields one task at a time
Compare the ClawGym-4B and ClawGym-8B model configs and tell me which to start with for a 24GB GPU
Set up a minimal RL training loop using the RL folder against the ClawGym-Trajectory dataset
Read the ClawGym arXiv preprint and summarize what a claw agent is and how trajectories are recorded
Full explanation on explaingit →
📎
Send
By chatting or signing in you agree to the
Terms
and chat-message logging (revocable in
History
).