zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-12-16 02:08:55 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'ml-explore:main' into adding-support-for-mamba2

Browse Source
This commit is contained in:
Gökdeniz Gülmez
2025-01-13 20:16:04 +01:00
committed by GitHub
parent 8deada9d11 c117af83b8
commit 5509ef8e52
59 changed files with 1272 additions and 279 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
llms/mlx_lm/LORA.md
View File

@@ -266,14 +266,25 @@ Refer to the documentation for the model you are fine-tuning for more details.
{"prompt": "What is the capital of France?", "completion": "Paris."}
```
For the `completions` data format, a different key can be used for the prompt
and completion by specifying the following in the YAML config:
```yaml
prompt_feature: "input"
completion_feature: "output"
```
Here, `"input"` is the expected key instead of the default `"prompt"`, and
`"output"` is the expected key instead of `"completion"`.
`text`:
```jsonl
{"text": "This is an example for the model."}
```
Note, the format is automatically determined by the dataset. Note also, keys in
each line not expected by the loader will be ignored.
Note, the format is automatically determined by the dataset. Note also, keys
in each line not expected by the loader will be ignored.
> [!NOTE]
> Each example in the datasets must be on a single line. Do not put more than
@@ -295,7 +306,7 @@ Otherwise, provide a mapping of keys in the dataset to the features MLX LM
expects. Use a YAML config to specify the Hugging Face dataset arguments. For
example:
```
```yaml
hf_dataset:
name: "billsum"
prompt_feature: "text"