mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-23 12:57:11 +00:00
06cb0c837e
## What does this PR do? - Add related Apis in experimental-post-training template to enable eval on the finetuned checkpoint in the template - A small bug fix on meta reference eval - A small error handle improvement on post training ## Test Plan From client side issued an E2E post training request https://github.com/meta-llama/llama-stack-client-python/pull/70 and get eval results successfully <img width="1315" alt="Screenshot 2024-12-20 at 12 06 59 PM" src="https://github.com/user-attachments/assets/a09bd524-59ae-490c-908f-2e36ccf27c0a" />
25 lines
527 B
YAML
25 lines
527 B
YAML
version: '2'
|
|
name: experimental-post-training
|
|
distribution_spec:
|
|
description: Experimental template for post training
|
|
docker_image: null
|
|
providers:
|
|
inference:
|
|
- inline::meta-reference
|
|
eval:
|
|
- inline::meta-reference
|
|
scoring:
|
|
- inline::basic
|
|
post_training:
|
|
- inline::torchtune
|
|
datasetio:
|
|
- remote::huggingface
|
|
telemetry:
|
|
- inline::meta-reference
|
|
agents:
|
|
- inline::meta-reference
|
|
safety:
|
|
- inline::llama-guard
|
|
memory:
|
|
- inline::faiss
|
|
image_type: conda
|