Spaces:
Sleeping
Sleeping
File size: 3,257 Bytes
a6194a4 5c7a9b7 a6194a4 5c7a9b7 528b563 a6194a4 5c7a9b7 a6194a4 5c7a9b7 a6194a4 5c7a9b7 a6194a4 5c7a9b7 a6194a4 26cc4a8 a6194a4 5c7a9b7 a6194a4 5c7a9b7 |
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 |
from huggingface_hub import InferenceClient
import gradio as gr
import os
import requests
client = InferenceClient(
"mistralai/Mixtral-8x7B-Instruct-v0.1"
)
def format_prompt(message, history):
prompt = prompt_file="pr.txt"
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 log_conversation(user_prompt, bot_response, log_file="text/dump.txt"):
# Write conversation to the chatinfo.txt file
with open(log_file, "a") as f:
f.write(f"User: {user_prompt}\n")
f.write(f"Bot: {bot_response}\n")
print(f"Conversation logged to {log_file}")
def generate(
prompt, history, temperature=0.1, max_new_tokens=4096, 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(f"{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
log_conversation(prompt, output)
if output.lower().strip() in ["hi", "hello", "hey"]:
output = "Hey, what's up? What are you looking for, my man?"
yield output
additional_inputs=[
gr.Slider(
label="Temperature",
value=0.1,
minimum=0.0,
maximum=1.0,
step=0.1,
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",
)
]
examples=[["Hi", None, None, None, None, None, ],
["Do you have exclusive contents planned for your subscribers soon?", None, None, None, None, None,],
["Can you tell me more about yourself?", None, None, None, None, None,],
["Tell me about how suck cock and swallow loads.", None, None, None, None, None,],
]
gr.ChatInterface(
fn=generate,
chatbot=gr.Chatbot(show_label=False, show_share_button=True, show_copy_button=True, likeable=True, layout="panel"),
additional_inputs=additional_inputs,
title="AmberBot ",
examples=examples,
concurrency_limit=128,
theme = gr.themes.Default(primary_hue= gr.themes.colors.green, secondary_hue= gr.themes.colors.yellow)
).launch(show_api=False, share=True) |