Spaces:

anugrah55
/

opensleuth-training-gemini-cli

Paused

50.9 kB

Ctrl+K

1 contributor

trainer v0.4: switch to Qwen2.5-3B-Instruct, dynamic task discovery, delegated probe sampling, difficulty-weighted rollouts, push to opensleuth-qwen2.5-3b-grpo-v2; sentinel cleared on FORCE_TRAIN=1.

78575eb verified 12 days ago

__pycache__
Overhaul trainer: TRL GRPO with env-backed reward, Qwen2.5-0.5B 4bit+LoRA, slim PyTorch CUDA base, heartbeat HTTP for HF Spaces health probe 12 days ago
opensleuth_train
trainer v0.4: switch to Qwen2.5-3B-Instruct, dynamic task discovery, delegated probe sampling, difficulty-weighted rollouts, push to opensleuth-qwen2.5-3b-grpo-v2; sentinel cleared on FORCE_TRAIN=1. 12 days ago
.gitattributes

1.52 kB
initial commit 13 days ago
Dockerfile

992 Bytes
Drop deprecated TRANSFORMERS_CACHE env var 12 days ago
README.md

1.98 kB
Overhaul trainer: TRL GRPO with env-backed reward, Qwen2.5-0.5B 4bit+LoRA, slim PyTorch CUDA base, heartbeat HTTP for HF Spaces health probe 12 days ago
entrypoint.sh

2.68 kB
trainer v0.4: switch to Qwen2.5-3B-Instruct, dynamic task discovery, delegated probe sampling, difficulty-weighted rollouts, push to opensleuth-qwen2.5-3b-grpo-v2; sentinel cleared on FORCE_TRAIN=1. 12 days ago
requirements.txt

401 Bytes
Bump TRL to 0.16.1 (adds GRPOTrainer); transformers 4.51.3, peft 0.14, accelerate 1.4, bnb 0.45.5 12 days ago
train.py

10.8 kB
trainer v0.4: switch to Qwen2.5-3B-Instruct, dynamic task discovery, delegated probe sampling, difficulty-weighted rollouts, push to opensleuth-qwen2.5-3b-grpo-v2; sentinel cleared on FORCE_TRAIN=1. 12 days ago