Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
anugrahhu
/
cernenv-trainer
like
0
Paused
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
cernenv-trainer
/
training
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
anugrahhu
sft+reward-fix: training/training_script.py
2b97998
verified
12 days ago
__init__.py
Safe
78 Bytes
Update CERNenv Space
13 days ago
colab_train_unsloth.ipynb
Safe
8.64 kB
Update CERNenv Space
13 days ago
curriculum.py
Safe
6.42 kB
Update CERNenv Space
13 days ago
evaluate.py
Safe
5.57 kB
fix: disable fast_inference (vLLM not installed) in training/evaluate.py
13 days ago
evidence.py
Safe
19.1 kB
Update CERNenv Space
13 days ago
llm_agent.py
Safe
7.97 kB
Update CERNenv Space
13 days ago
plots.py
Safe
3.3 kB
Update CERNenv Space
13 days ago
rollouts.py
Safe
4.75 kB
Update CERNenv Space
13 days ago
sft_warmstart.py
Safe
15.7 kB
sft+reward-fix: training/sft_warmstart.py
12 days ago
training_script.py
Safe
24.2 kB
sft+reward-fix: training/training_script.py
12 days ago
training_unsloth.py
Safe
14.9 kB
fix: disable fast_inference (vLLM not installed) in training/training_unsloth.py
13 days ago
