mirror/gradio
2
0
Fork 0
mirror of https://github.com/gradio-app/gradio.git synced 2025-04-12 12:40:29 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fixed redirects and reformatted code in creating-a-fast-chatbot guide (#7563)

Browse Source 
* Minor code styling fix in example to be more consistent

* Fix broken redirect

* Fixed two more redirects

* Fixed more redirects

* Revert faulty redirect updates
This commit is contained in:
André Pedersen 2024-02-28 23:56:29 +01:00 committed by GitHub
parent bd2c695328
commit 24626ea362
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
guides/04_chatbots/01_creating-a-chatbot-fast.md
View File

@ -248,11 +248,10 @@ class StopOnTokens(StoppingCriteria):
return False
def predict(message, history):
history_transformer_format = history + [[message, ""]]
stop = StopOnTokens()
messages = "".join(["".join(["\n<human>:"+item[0], "\n<bot>:"+item[1]]) #curr_system_message +
messages = "".join(["".join(["\n<human>:"+item[0], "\n<bot>:"+item[1]])
for item in history_transformer_format])
model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
@ -271,13 +270,12 @@ def predict(message, history):
t = Thread(target=model.generate, kwargs=generate_kwargs)
t.start()
partial_message = ""
partial_message = ""
for new_token in streamer:
if new_token != '<':
partial_message += new_token
yield partial_message
gr.ChatInterface(predict).launch()
```