Skip to content
Arm
Git
Search or jump to…
Ctrl K
Categories
Theme: System
Sign in
Get started
armgit
/
train-llm-from-scratch
Public
Imported from GitHub
Fork
0
Watch
0
Star
0
A straightforward method for training your LLM, from downloading data to generating text.
Python
gemini
large-language-models
llm
openai
training
transformers
Code
Commits
Issues
Pull requests
Wiki
Builds
Discussions
Projects
Insights
Search
Files
main
7 branches · 0 tags
Go to file
t
Code
train-llm-from-scratch
/
scripts
Name
Last commit message
Last commit date
..
PY
benchmark.py
4.4 KB
PY
chat.py
3.1 KB
PY
data_download.py
4.1 KB
PY
data_preprocess.py
5.8 KB
PY
eval_post_training.py
2.9 KB
PY
generate_text.py
7.9 KB
PY
model_report.py
6.6 KB
PY
prepare_preference_data.py
3.7 KB
PY
prepare_pretrain_data.py
4.7 KB
PY
prepare_rl_prompts.py
2.6 KB
PY
prepare_sft_data.py
5.1 KB
PY
prepare_tiny_data.py
8.6 KB
PY
pretrain_base.py
6.8 KB
SH
render_diagrams.sh
1.3 KB
SH
run_posttraining.sh
1.9 KB
PY
train_dpo.py
7.0 KB
PY
train_grpo.py
8.4 KB
PY
train_ppo.py
8.8 KB
PY
train_reward.py
5.7 KB
PY
train_sft.py
6.8 KB
PY
train_transformer.py
31.3 KB