File size: 8,436 Bytes
2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 b8f046a 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 2066897 0d2c1e4 ac93498 0d2c1e4 ac93498 0d2c1e4 ac93498 0d2c1e4 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 |
# import streamlit as st
# from openai import OpenAI
# import os
# import sys
# from dotenv import load_dotenv, dotenv_values
# load_dotenv()
# # initialize the client
# client = OpenAI(
# base_url="https://api-inference.huggingface.co/v1",
# api_key=os.environ.get('HUGGINGFACEHUB_API_TOKEN')#"hf_xxx" # Replace with your token
# )
# #Create supported models
# model_links ={
# "Mistral-7b":"mistralai/Mistral-7B-Instruct-v0.2",
# "Mistral-8x7b":"mistralai/Mixtral-8x7B-Instruct-v0.1"
# # "Gemma-7B":"google/gemma-7b-it",
# # "Gemma-2B":"google/gemma-2b-it",
# # "Zephyr-7B-β":"HuggingFaceH4/zephyr-7b-beta",
# }
# #Pull info about the model to display
# model_info ={
# "Mistral-7b":
# {'description':"""The Mistral 7B model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n \
# \nIt was created by the [**Mistral AI**](https://mistral.ai/news/announcing-mistral-7b/) team as has over **7 billion parameters.** \n""",
# 'logo':'https://mistral.ai/images/logo_hubc88c4ece131b91c7cb753f40e9e1cc5_2589_256x0_resize_q97_h2_lanczos_3.webp'},
# "Mistral-8x7b":
# {'description':"""The Mistral 8x7B model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n \
# \nIt was created by the [**Mistral AI**](https://mistral.ai/news/announcing-mistral-8x7b/) team as has based on MOE arch.** \n""",
# 'logo':'https://mistral.ai/images/logo_hubc88c4ece131b91c7cb753f40e9e1cc5_2589_256x0_resize_q97_h2_lanczos_3.webp'},
# # "Gemma-7B":
# # {'description':"""The Gemma model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n \
# # \nIt was created by the [**Google's AI Team**](https://blog.google/technology/developers/gemma-open-models/) team as has over **7 billion parameters.** \n""",
# # 'logo':'https://pbs.twimg.com/media/GG3sJg7X0AEaNIq.jpg'},
# # "Gemma-2B":
# # {'description':"""The Gemma model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n \
# # \nIt was created by the [**Google's AI Team**](https://blog.google/technology/developers/gemma-open-models/) team as has over **2 billion parameters.** \n""",
# # 'logo':'https://pbs.twimg.com/media/GG3sJg7X0AEaNIq.jpg'},
# # "Zephyr-7B":
# # {'description':"""The Zephyr model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n \
# # \nFrom Huggingface: \n\
# # Zephyr is a series of language models that are trained to act as helpful assistants. \
# # [Zephyr 7B Gemma](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1)\
# # is the third model in the series, and is a fine-tuned version of google/gemma-7b \
# # that was trained on on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO)\n""",
# # 'logo':'https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1/resolve/main/thumbnail.png'},
# # "Zephyr-7B-β":
# # {'description':"""The Zephyr model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n \
# # \nFrom Huggingface: \n\
# # Zephyr is a series of language models that are trained to act as helpful assistants. \
# # [Zephyr-7B-β](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)\
# # is the second model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 \
# # that was trained on on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO)\n""",
# # 'logo':'https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/resolve/main/thumbnail.png'},
# }
# def reset_conversation():
# '''
# Resets Conversation
# '''
# st.session_state.conversation = []
# st.session_state.messages = []
# return None
# # Define the available models
# models =[key for key in model_links.keys()]
# # Create the sidebar with the dropdown for model selection
# selected_model = st.sidebar.selectbox("Select Model", models)
# #Create a temperature slider
# temp_values = st.sidebar.slider('Select a temperature value', 0.0, 1.0, (0.5))
# #Add reset button to clear conversation
# st.sidebar.button('Reset Chat', on_click=reset_conversation) #Reset button
# # Create model description
# st.sidebar.write(f"You're now chatting with **{selected_model}**")
# st.sidebar.markdown(model_info[selected_model]['description'])
# st.sidebar.image(model_info[selected_model]['logo'])
# # st.sidebar.markdown("*Generated content may be inaccurate or false.*")
# # st.sidebar.markdown("\nLearn how to build this chatbot [here](https://ngebodh.github.io/projects/2024-03-05/).")
# # st.sidebar.markdown("\nRun into issues? Try the [back-up](https://huggingface.co/spaces/ngebodh/SimpleChatbot-Backup).")
# if "prev_option" not in st.session_state:
# st.session_state.prev_option = selected_model
# if st.session_state.prev_option != selected_model:
# st.session_state.messages = []
# # st.write(f"Changed to {selected_model}")
# st.session_state.prev_option = selected_model
# reset_conversation()
# #Pull in the model we want to use
# repo_id = model_links[selected_model]
# st.subheader(f'AI - {selected_model}')
# # st.title(f'ChatBot Using {selected_model}')
# # Set a default model
# if selected_model not in st.session_state:
# st.session_state[selected_model] = model_links[selected_model]
# # Initialize chat history
# if "messages" not in st.session_state:
# st.session_state.messages = []
# # Display chat messages from history on app rerun
# for message in st.session_state.messages:
# with st.chat_message(message["role"]):
# st.markdown(message["content"])
# # Accept user input
# if prompt := st.chat_input(f"Hi I'm {selected_model}, ask me a question"):
# # Display user message in chat message container
# with st.chat_message("user"):
# st.markdown(prompt)
# # Add user message to chat history
# st.session_state.messages.append({"role": "user", "content": prompt})
# # Display assistant response in chat message container
# with st.chat_message("assistant"):
# stream = client.chat.completions.create(
# model=model_links[selected_model],
# messages=[
# {"role": m["role"], "content": m["content"]}
# for m in st.session_state.messages
# ],
# temperature=temp_values,#0.5,
# stream=True,
# max_tokens=3000,
# )
# response = st.write_stream(stream)
# st.session_state.messages.append({"role": "assistant", "content": response})
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=0.2, max_new_tokens=3000, 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
mychatbot = gr.Chatbot(
avatar_images=["./user.png", "./bot.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
demo = gr.ChatInterface(fn=generate,
chatbot=mychatbot,
title="Mistral-Chat",
retry_btn=None,
undo_btn=None
)
demo.queue().launch(show_api=False) |