Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

feat: include local lora adapter loading docs (#2359)

This commit is contained in:
drbh 2024-08-05 12:36:44 -04:00 committed by GitHub
parent 215ed3ad52
commit dd47a3dac4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
docs/source/conceptual/lora.md
View File

@ -36,6 +36,18 @@ To use LoRA in TGI, when starting the server, you can specify the list of LoRA m
LORA_ADAPTERS=predibase/customer_support,predibase/dbpedia LORA_ADAPTERS=predibase/customer_support,predibase/dbpedia
``` ```
additionally, you can specify the path to the LoRA models using the `LORA_ADAPTERS_PATH` environment variable. For example:
```bash
LORA_ADAPTERS=myadapter=/some/path/to/adapter,myadapter2=/another/path/to/adapter
```
note it's possible to mix adapter_ids with adapter_id=adapter_path e.g.
```bash
LORA_ADAPTERS=predibase/dbpedia,myadapter=/path/to/dir/
```
In the server logs, you will see the following message: In the server logs, you will see the following message:
```txt ```txt