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
/
docs
/
diagrams
/
src
Name
Last commit message
Last commit date
..
00_overview.mmd
1.1 KB
01_data_pipeline.mmd
1.4 KB
02_pretraining.mmd
915 B
03_sft.mmd
881 B
04_reward_model.mmd
896 B
05_dpo.mmd
870 B
06_ppo.mmd
956 B
07_grpo.mmd
926 B
08_evaluation.mmd
773 B
09_inference.mmd
795 B
16_modern_block.mmd
1.1 KB
17_gqa.mmd
1.2 KB
18_kv_cache.mmd
808 B
19_moe.mmd
1.1 KB
20_grpo_variants.mmd
1.2 KB
21_student_track.mmd
951 B
22_lora.mmd
887 B
23_speculative.mmd
1016 B
24_bpe.mmd
1.1 KB
25_typed_config.mmd
996 B
README.mmd
1.1 KB