Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

V1.2.0 cicl #214

Closed
wants to merge 37 commits into from
Closed

V1.2.0 cicl #214

wants to merge 37 commits into from

Conversation

reymondzzzz
Copy link
Member

No description provided.

mitya52 and others added 30 commits November 1, 2023 10:02
* Print statements for debugging and initial support for Code Llama

* Added multiple print statements for debugging fine tuning
* Added support for Code Llama 7b
* Depending on the training parameters I set I either get an out of memory GPU error or ValueError(“optimizer got an empty parameter list”)

* Code Llama fine-tuning but fails on checkpoint

* commenting print statements

* updating default config behavior

* Begin adding encoding for Code Llama

* adding BOS and EOS tokens for Code Llama, model running properly

* getting rid of #?

* Print statements for debugging and initial support for Code Llama

* Added multiple print statements for debugging fine tuning
* Added support for Code Llama 7b
* Depending on the training parameters I set I either get an out of memory GPU error or ValueError(“optimizer got an empty parameter list”)

* Code Llama fine-tuning but fails on checkpoint

* commenting print statements

* updating default config behavior

* Begin adding encoding for Code Llama

* adding BOS and EOS tokens for Code Llama, model running properly

* getting rid of #?
saving in safe_tensors format
TOKENIZERS_PARALLELISM=false while finetuning
add inference fixes for codellama
* add deepseek inference and finetuning

* no extra kwargs

* add deepseek-ai/deepseek-coder-5.7bmqa-base
@reymondzzzz reymondzzzz closed this Nov 8, 2023
@klink klink linked an issue Nov 9, 2023 that may be closed by this pull request
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

add check for the minumum number of files for fine-tuning job
6 participants