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

Update code blocks huggingface.md (#6737)

Browse source
This commit is contained in:
Jongseob Jeon 2024-11-14 13:47:57 +08:00 • committed by GitHub
parent 310669e3bc
commit f3914c87d3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 5 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
docs/my-website/docs/providers/huggingface.md
View file

@ -37,7 +37,7 @@ os.environ["HUGGINGFACE_API_KEY"] = "huggingface_api_key"
messages = [{ "content": "There's a llama in my garden 😱 What should I do?","role": "user"}] messages = [{ "content": "There's a llama in my garden 😱 What should I do?","role": "user"}]
# e.g. Call 'https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct' from Serverless Inference API # e.g. Call 'https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct' from Serverless Inference API
response = litellm.completion( response = completion(
model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct", model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct",
messages=[{ "content": "Hello, how are you?","role": "user"}], messages=[{ "content": "Hello, how are you?","role": "user"}],
stream=True stream=True
@ -165,14 +165,14 @@ Steps to use
```python ```python
import os import os
import litellm from litellm import completion
os.environ["HUGGINGFACE_API_KEY"] = "" os.environ["HUGGINGFACE_API_KEY"] = ""
# TGI model: Call https://huggingface.co/glaiveai/glaive-coder-7b # TGI model: Call https://huggingface.co/glaiveai/glaive-coder-7b
# add the 'huggingface/' prefix to the model to set huggingface as the provider # add the 'huggingface/' prefix to the model to set huggingface as the provider
# set api base to your deployed api endpoint from hugging face # set api base to your deployed api endpoint from hugging face
response = litellm.completion( response = completion(
model="huggingface/glaiveai/glaive-coder-7b", model="huggingface/glaiveai/glaive-coder-7b",
messages=[{ "content": "Hello, how are you?","role": "user"}], messages=[{ "content": "Hello, how are you?","role": "user"}],
api_base="https://wjiegasee9bmqke2.us-east-1.aws.endpoints.huggingface.cloud" api_base="https://wjiegasee9bmqke2.us-east-1.aws.endpoints.huggingface.cloud"
@ -383,6 +383,8 @@ def default_pt(messages):
#### Custom prompt templates #### Custom prompt templates
```python ```python
import litellm
# Create your own custom prompt template works # Create your own custom prompt template works
litellm.register_prompt_template( litellm.register_prompt_template(
model="togethercomputer/LLaMA-2-7B-32K", model="togethercomputer/LLaMA-2-7B-32K",