phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-25 16:38:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

even more fixes

Browse source
This commit is contained in:
Ashwin Bharambe 2025-08-05 14:52:09 -07:00
parent 0b6a7abb28
commit 882176928f
16 changed files with 28 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

3
docs/source/providers/post_training/inline_huggingface.md
View file

@ -27,7 +27,7 @@ HuggingFace-based post-training provider for fine-tuning models using the Huggin
| `dpo_beta` | `<class 'float'>` | No | 0.1 | |
| `use_reference_model` | `<class 'bool'>` | No | True | |
| `dpo_loss_type` | `Literal['sigmoid', 'hinge', 'ipo', 'kto_pair'` | No | sigmoid | |
| `dpo_output_dir` | `<class 'str'>` | No | /var/folders/mj/t_stv1ys7637vqf2_b4yf67m0000gn/T/dpo_output_q24jwy0r | |
| `dpo_output_dir` | `<class 'str'>` | No | | |
## Sample Configuration
@ -35,6 +35,7 @@ HuggingFace-based post-training provider for fine-tuning models using the Huggin
checkpoint_format: huggingface
distributed_backend: null
device: cpu
dpo_output_dir: ~/.llama/dummy/dpo_output
```