Spaces:
Sleeping
Sleeping
File size: 3,047 Bytes
17cf727 1a7e5d6 17cf727 027d8aa 02fcf54 027d8aa 02fcf54 17cf727 1a7e5d6 17cf727 027d8aa 17cf727 027d8aa 02fcf54 17cf727 1a7e5d6 17cf727 027d8aa 17cf727 |
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 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
from huggingface_hub import InferenceClient
from fastapi import FastAPI
from pydantic import BaseModel
import gradio as gr
client = InferenceClient(
"mistralai/Mistral-7B-Instruct-v0.3"
)
def format_prompt(message, history, system_message=None):
prompt = "<s>"
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST]"
prompt += f" {bot_response}</s> "
if system_message:
prompt += f"[SYS] {system_message} [/SYS]"
prompt += f"[INST] {message} [/INST]"
return prompt
def generate(
prompt, history, system_message=None, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=42,
)
formatted_prompt = format_prompt(prompt, history, system_message)
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
additional_inputs=[
gr.TextArea(
label="System message",
value="",
interactive=True,
info="context",
),
gr.Slider(
label="Temperature",
value=0.9,
minimum=0.0,
maximum=1.0,
step=0.05,
interactive=True,
info="Higher values produce more diverse outputs",
),
gr.Slider(
label="Max new tokens",
value=256,
minimum=0,
maximum=1048,
step=64,
interactive=True,
info="The maximum numbers of new tokens",
),
gr.Slider(
label="Top-p (nucleus sampling)",
value=0.90,
minimum=0.0,
maximum=1,
step=0.05,
interactive=True,
info="Higher values sample more low-probability tokens",
),
gr.Slider(
label="Repetition penalty",
value=1.2,
minimum=1.0,
maximum=2.0,
step=0.05,
interactive=True,
info="Penalize repeated tokens",
)
]
class Item(BaseModel):
prompt: str
history: list
system_prompt: str
temperature: float = 0.0
max_new_tokens: int = 1048
top_p: float = 0.15
repetition_penalty: float = 1.0
app = FastAPI()
@app.post("/generate/")
async def generate_text(item: Item):
return {"response": generate(item.prompt, item.history, item.system_message, item.temperature, item.max_new_tokens, item.top_p, item.repetition_penalty)}
gr.ChatInterface(
fn=generate,
chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
additional_inputs=additional_inputs,
title="""mistralai/Mistral-7B-Instruct-v0.3"""
).launch(show_api=False) |