add doc

huggingface · Feb 10, 2025 · 9a7ace0 · 9a7ace0
1 parent e5b63ef
commit 9a7ace0
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 1 deletion.
diff --git a/docs/assets/litellm-guide-1.png → docs/imgs/litellm-guide-1.png b/docs/assets/litellm-guide-1.png → docs/imgs/litellm-guide-1.png
diff --git a/docs/assets/litellm-guide-2.png → docs/imgs/litellm-guide-2.png b/docs/assets/litellm-guide-2.png → docs/imgs/litellm-guide-2.png
diff --git a/docs/source/use-litellm-as-backend.mdx b/docs/source/use-litellm-as-backend.mdx
@@ -4,6 +4,8 @@ Lighteval allows to use litellm, a backend allowing you to call all LLM APIs
 using the OpenAI format [Bedrock, Huggingface, VertexAI, TogetherAI, Azure,
 OpenAI, Groq etc.].
 
+Documentation for available APIs and compatible endpoints can be found [here](https://docs.litellm.ai/docs/).
+
 ## Quick use
 
 ```bash
@@ -35,11 +37,13 @@ model:
     frequency_penalty: 0.0
 ```
 
+## Use huggingface inference API
+
 With this you can also access HuggingFace Inference servers, let's look at how to evaluate DeepSeek-R1-Distill-Qwen-32B.
 
 First, let's look at how to acess the model, we can find this from [the model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B).
 
-![Step 1]("../assets/litellm-guide-1.png")
+![Step 1]("/imgs/litellm-guide-1.png")
 
 Great ! Now we can simply copy paste the base_url and our api key to eval our model.