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

Feat: Add example for Mistral #644

Merged
merged 4 commits into from
Sep 28, 2023

Conversation

NanoCode012
Copy link
Collaborator

@NanoCode012 NanoCode012 commented Sep 27, 2023

Todo:

  • Update transformer commit

In future PR, allow sample_packing.

Upstream PR: huggingface/transformers#26447

@@ -0,0 +1,69 @@
base_model: mistralai/Mistral-7B-v0.1
base_model_config: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should be able to use AutoModelForCausalLM

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, but I think it would be better to specify for later parsing (aka is_mistral_derived..)

@winglian
Copy link
Collaborator

let's use [78dd120](https://github.com/huggingface/transformers/commit/78dd1202823ca035b9609ddbcdaac2945a6530ff)

@winglian
Copy link
Collaborator

this PR should fix the issues we were having w transformers main that we had to pin it in the first place #636

@winglian
Copy link
Collaborator

also, see #646

@NanoCode012 NanoCode012 marked this pull request as ready for review September 28, 2023 01:31
@NanoCode012 NanoCode012 merged commit eb41f76 into axolotl-ai-cloud:main Sep 28, 2023
4 checks passed
@NanoCode012 NanoCode012 deleted the feat/mistral branch September 28, 2023 11:15
mkeoliya pushed a commit to mkeoliya/axolotl that referenced this pull request Dec 15, 2023
* Feat: Add example for Mistral

* chore: turn off flash

* chore: add is_mistral_derived_model

* chore: update following PR
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.

None yet

3 participants