Spaces:
Runtime error
Runtime error
File size: 2,312 Bytes
b65b6c0 edeb481 4d0c690 66128ec b65b6c0 4d0c690 b65b6c0 9b1893a 66128ec 4d0c690 2952141 66128ec 7aacca6 66128ec ac300f9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
import gradio as gr
from huggingface_hub import InferenceClient
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("meta-llama/Meta-Llama-3-8B")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
def chat_function(message, history, system_prompt, max_new_tokens, temperature):
messages = [{"role":"system","content":system_prompt},
{"role":"user", "content":message}]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")]
outputs = pipeline(
prompt,
max_new_tokens = max_new_tokens,
eos_token_id = terminators,
do_sample = True,
temperature = temperature + 0.1,
top_p = 0.9,)
return outputs[0]["generated_text"][len(prompt):]
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
chat_function,
textbox=gr.Textbox(placeholder="Enter message here", container=False, scale = 7),
chatbot=gr.Chatbot(height=400),
additional_inputs=[
gr.Textbox("You are helpful AI", label="System Prompt"),
gr.Slider(500,4000, label="Max New Tokens"),
gr.Slider(0,1, label="Temperature", value= 0.7)
],
)
if __name__ == "__main__":
demo.launch() |