Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
cafaxo
11 months ago
|
parent
|
context
|
favorite
| on:
Building an LLM from Scratch: Automatic Differenti...
I did a similar thing for Julia: Llama2.jl contains vanilla Julia code [1] for training small Llama2-style models on the CPU.
[1]
https://github.com/cafaxo/Llama2.jl/tree/master/src/training
3abiton
11 months ago
|
next
[–]
How hard was it to find open source data nowadays? I saw that books3 are already made illegal to train on.
andxor_
11 months ago
|
prev
[–]
Great stuff. Thanks for sharing.
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
[1] https://github.com/cafaxo/Llama2.jl/tree/master/src/training