phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

doc cleanup

Browse source
This commit is contained in:
Krrish Dholakia 2023-08-14 14:55:11 -07:00
parent 54cbf41fd9
commit f2d60e87ec
1 changed files with 7 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

11
docs/my-website/docs/tutorials/huggingface_tutorial.md
View file

@ -4,10 +4,13 @@
## Call Llama2 with Huggingface Inference Endpoints ## Call Llama2 with Huggingface Inference Endpoints
LiteLLM makes it easy to call your public, private or the default huggingface endpoints. LiteLLM makes it easy to call your public, private or the default huggingface endpoints.
In this case, let's try and call 3 models: In this case, let's try and call 3 models:
- `deepset/deberta-v3-large-squad2`: calls the default huggingface endpoint
- `meta-llama/Llama-2-7b-hf`: calls a public endpoint | Model | Type of Endpoint |
- `meta-llama/Llama-2-7b-chat-hf`: call your privat endpoint | --------------------------------------- | ---------------- |
| deepset/deberta-v3-large-squad2 | [Default Huggingface Endpoint](#case-1-call-default-huggingface-endpoint) |
| meta-llama/Llama-2-7b-hf | [Public Endpoint](#case-2-call-llama2-public-huggingface-endpoint) |
| meta-llama/Llama-2-7b-chat-hf | [Private Endpoint](#case-3-call-llama2-private-huggingface-endpoint) |
### Case 1: Call default huggingface endpoint ### Case 1: Call default huggingface endpoint