fix: :bug: fix replicate to work with models requiring prompt input

1 files changed, 3 insertions, 3 deletions

diff --git a/docs/docs/customization.md b/docs/docs/customization.md
index a3774e91..b7279fe3 100644
--- a/docs/docs/customization.md
+++ b/docs/docs/customization.md
@@ -117,7 +117,7 @@ config = ContinueConfig(
 )
 ```
 
-### Replicate (beta)
+### Replicate
 
 Replicate is a great option for newly released language models or models that you've deployed through their platform. Sign up for an account [here](https://replicate.ai/), copy your API key, and then select any model from the [Replicate Streaming List](https://replicate.com/collections/streaming-language-models). Change `~/.continue/config.py` to look like this:
 
@@ -129,13 +129,13 @@ config = ContinueConfig(
     ...
     models=Models(
         default=ReplicateLLM(
-            model="stablecode-completion-alpha-3b-4k",
+            model="replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781",
             api_key="my-replicate-api-key")
     )
 )
 ```
 
-If you don't specify the `model` parameter, it will default to `stablecode-completion-alpha-3b-4k`.
+If you don't specify the `model` parameter, it will default to `replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781`.
 
 ### Self-hosting an open-source model