mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-10 20:04:52 +00:00
nit
This commit is contained in:
parent
eb8f59083d
commit
9a0a4d926c
@ -28,7 +28,8 @@ AutoModelForCausalLM.from_pretrained(<model>, device_map="auto")`
|
||||
AutoModelForSeq2SeqLM.from_pretrained(<model>, device_map="auto")
|
||||
```
|
||||
|
||||
If you wish to serve a different version of a model that exists in a local folder, you can use `weight-cache-override` flag like below 👇
|
||||
If you wish to serve a supported model that already exists on a local folder, you can use `weight-cache-override` flag like below. Otherwise, it will be downloaded to Hugging Face Hub cache.
|
||||
|
||||
```bash
|
||||
text-generation-launcher --model-id bigscience/bloom --weights-cache-override <PATH-TO-LOCAL-BLOOM>
|
||||
```
|
||||
|
Loading…
Reference in New Issue
Block a user