Spaces:
Sleeping
Sleeping
File size: 1,268 Bytes
5c0e14a 69b2fee 5c0e14a c73295d 5c0e14a 0ef4d3d c73295d 0ef4d3d 5c0e14a 89180ff 5c0e14a 17fba42 4010b81 8549fec 0ef4d3d 8549fec |
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 |
from huggingface_hub import InferenceClient
import gradio as gr
client = InferenceClient(
"mistralai/Mistral-7B-Instruct-v0.2"
)
def format_prompt(message, history):
prompt = "<s>"
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST]"
prompt += f" {bot_response}</s> "
prompt += f"[INST] {message} [/INST]"
return prompt
def generate(
prompt, history, temperature=0.9, max_new_tokens=16000, top_p=0.95, repetition_penalty=1.0,
):
generate_kwargs = dict(
temperature=0.9,
max_new_tokens=16000,
top_p=0.9,
repetition_penalty=1.0,
do_sample=True,
stop_sequence = ".",
seed=42,
)
formatted_prompt = format_prompt(prompt, history)
stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
output = ""
for response in stream:
output += response.token.text
yield output
return output
css = """
#mkd {
height: 500px;
overflow: auto;
border: 1px solid #ccc;
}
"""
with gr.Blocks(css=css) as demo:
gr.HTML("<h1><center>Mistral 7B Instruct<h1><center>")
gr.ChatInterface(
generate
)
demo.queue().launch(debug=True) |