zjrwtx's picture
Update app.py
9a1a910
from huggingface_hub import InferenceClient
import gradio as gr
API_URL = "https://api-inference.huggingface.co/models/"
client = InferenceClient(
"mistralai/Mistral-7B-Instruct-v0.1"
)
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=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)
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.Slider(
label="随机性",
value=0.9,
minimum=0.0,
maximum=1.0,
step=0.05,
interactive=True,
info="公众号正经人王同学:值越高随机性多样性越高",
),
gr.Slider(
label="生成的回答的最大长度",
value=256,
minimum=0,
maximum=1048,
step=64,
interactive=True,
info="公众号正经人王同学:值越高生成的回答长度越长",
),
gr.Slider(
label="概率标记",
value=0.90,
minimum=0.0,
maximum=1,
step=0.05,
interactive=True,
info="公众号正经人王同学:较高的值代表更多的低概率标记",
),
gr.Slider(
label="重复性",
value=1.2,
minimum=1.0,
maximum=2.0,
step=0.05,
interactive=True,
info="公众号正经人王同学:重复性值",
)
]
with gr.Blocks() as demo:
gr.Markdown("""
## 正经人王同学的吾湖mini1 迷你一代模型更快更省资源
**出品自公众号 [正经人王同学](https://mp.weixin.qq.com/s?__biz=Mzg3ODcwNzk3Nw==&mid=2247486555&idx=1&sn=1ed783c2c8b8faab0b7d83141f05e9b8&chksm=cf0ed83df879512bb61088c1dfe799e669a2e0b3dd9e0f38db033bc6eb777259d46a15433339&scene=126&sessionid=1697429440&poc_token=HMW3LGWjq2EcE4ZvssZZCb2qFZn4KcwW7tflxgOF) 欢迎新朋友滴滴王同学**
**微信:agi_isallyouneed(无备注不通过)**
**官网:[正经人王同学的AI实验室](https://www.yuque.com/zjrwtx)**
""")
gr.ChatInterface(
generate,
additional_inputs=additional_inputs,
)
demo.queue().launch(debug=True)