Update LLM_inference_endpoint.md

nata108 · web-flow · commit 7ae2a1cac047 · 2024-11-19T21:02:22.000+01:00
diff --git a/practice_examples/LLM_inference_endpoint.md b/practice_examples/LLM_inference_endpoint.md
@@ -80,7 +80,7 @@ data = {
         'max_new_tokens': 20,
     },
 }
-response = requests.post('http://127.0.0.1:8080/generate', headers=headers, json=data)
+response = requests.post('http://mobydick.elte-dh.hu:12321/generate', headers=headers, json=data)
 ```
 
 Some functionalities are not available via the OpenAI package (nor the official Huggingface Hub Client), such as listing the available model information, or performing tokenizations, health checks, etc. Check the API documentation for more details.

Original file line number	Diff line number	Diff line change
`@@ -80,7 +80,7 @@ data = {`
`80`	`80`	`'max_new_tokens': 20,`
`81`	`81`	`},`
`82`	`82`	`}`
`83`		`-response = requests.post('http://127.0.0.1:8080/generate', headers=headers, json=data)`
	`83`	`+response = requests.post('http://mobydick.elte-dh.hu:12321/generate', headers=headers, json=data)`
`84`	`84`	```
`85`	`85`
`86`	`86`	`Some functionalities are not available via the OpenAI package (nor the official Huggingface Hub Client), such as listing the available model information, or performing tokenizations, health checks, etc. Check the API documentation for more details.`