Neha12210
/

project1-math-reasoning-llm

Model card Files Files and versions

project1-math-reasoning-llm

83.2 kB

Ctrl+K

Ctrl+K

1 contributor

History: 20 commits

Neha12210's picture

add 03_evaluation.ipynb — proper Kaggle notebook with separate cells

af9071d verified 4 months ago

.gitattributes

1.52 kB
initial commit 4 months ago
01_sft_training.ipynb

6.89 kB
add 01_sft_training.ipynb — proper Kaggle notebook with separate cells 4 months ago
01_sft_training.py

6.99 kB
fix: audit all APIs for TRL 0.24.0 / PyTorch 2.10 compatibility 4 months ago
02_grpo_training.ipynb

11.2 kB
add 02_grpo_training.ipynb — proper Kaggle notebook with separate cells 4 months ago
02_grpo_training.py

11 kB
fix: num_generations=2 for T4x2 + add completion_ids to reward funcs (TRL 0.24) 4 months ago
03_evaluation.ipynb

12.6 kB
add 03_evaluation.ipynb — proper Kaggle notebook with separate cells 4 months ago
03_evaluation.py

11.6 kB
fix: audit all APIs for TRL 0.24.0 / PyTorch 2.10 compatibility 4 months ago
README.md

5.38 kB
Upload README.md with huggingface_hub 4 months ago
kaggle_notebook_grpo.py

9.91 kB
fix: num_generations=2 for T4x2 + add completion_ids to reward funcs (TRL 0.24) 4 months ago
kaggle_notebook_sft.py

6.03 kB
fix: audit all APIs for TRL 0.24.0 / PyTorch 2.10 compatibility 4 months ago
requirements.txt

214 Bytes
Upload requirements.txt with huggingface_hub 4 months ago