import numpy as np import streamlit as st from openai import OpenAI import os from dotenv import load_dotenv # Load environment variables load_dotenv() # Initialize the Hugging Face client hf_api_key = os.getenv('HF_API_KEY') # Replace with your Hugging Face API key openai_api_key = os.getenv('OPENAI_API_KEY') # Replace with your OpenAI API key client = OpenAI( api_key=openai_api_key ) # Create supported models model_links = { "Meta-Llama-3.1-70B-Instruct": "meta-llama/Meta-Llama-3.1-70B-Instruct", "Meta-Llama-3.1-8B-Instruct": "meta-llama/Meta-Llama-3.1-8B-Instruct", "Meta-Llama-3.1-405B-Instruct-FP8": "meta-llama/Meta-Llama-3.1-405B-Instruct-FP8", "Meta-Llama-3.1-405B-Instruct": "meta-llama/Meta-Llama-3.1-405B-Instruct", "Mistral-Nemo-Instruct-2407": "mistralai/Mistral-Nemo-Instruct-2407", "Meta-Llama-3-70B-Instruct": "meta-llama/Meta-Llama-3-70B-Instruct", "Meta-Llama-3-8B-Instruct": "meta-llama/Meta-Llama-3-8B-Instruct", "C4ai-command-r-plus": "CohereForAI/c4ai-command-r-plus", "Aya-23-35B": "CohereForAI/aya-23-35B", "Zephyr-orpo-141b-A35b-v0.1": "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1", "Mixtral-8x7B-Instruct-v0.1": "mistralai/Mixtral-8x7B-Instruct-v0.1", "Codestral-22B-v0.1": "mistralai/Codestral-22B-v0.1", "Nous-Hermes-2-Mixtral-8x7B-DPO": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO", "Yi-1.5-34B-Chat": "01-ai/Yi-1.5-34B-Chat", "Gemma-2-27b-it": "google/gemma-2-27b-it", "Meta-Llama-2-70B-Chat-HF": "meta-llama/Llama-2-70b-chat-hf", "Meta-Llama-2-7B-Chat-HF": "meta-llama/Llama-2-7b-chat-hf", "Meta-Llama-2-13B-Chat-HF": "meta-llama/Llama-2-13b-chat-hf", "Mistral-7B-Instruct-v0.1": "mistralai/Mistral-7B-Instruct-v0.1", "Mistral-7B-Instruct-v0.2": "mistralai/Mistral-7B-Instruct-v0.2", "Mistral-7B-Instruct-v0.3": "mistralai/Mistral-7B-Instruct-v0.3", "Falcon-7b-Instruct": "tiiuae/falcon-7b-instruct", "Starchat2-15b-v0.1": "HuggingFaceH4/starchat2-15b-v0.1", "Gemma-1.1-7b-it": "google/gemma-1.1-7b-it", "Gemma-1.1-2b-it": "google/gemma-1.1-2b-it", "Zephyr-7B-Beta": "HuggingFaceH4/zephyr-7b-beta", "Zephyr-7B-Alpha": "HuggingFaceH4/zephyr-7b-alpha", "Phi-3-mini-128k-instruct": "microsoft/Phi-3-mini-128k-instruct", "Phi-3-mini-4k-instruct": "microsoft/Phi-3-mini-4k-instruct", } # Random dog images for error message random_dog = ["0f476473-2d8b-415e-b944-483768418a95.jpg", "1bd75c81-f1d7-4e55-9310-a27595fa8762.jpg", "526590d2-8817-4ff0-8c62-fdcba5306d02.jpg", "1326984c-39b0-492c-a773-f120d747a7e2.jpg", "42a98d03-5ed7-4b3b-af89-7c4876cb14c3.jpg", "8b3317ed-2083-42ac-a575-7ae45f9fdc0d.jpg", "ee17f54a-83ac-44a3-8a35-e89ff7153fb4.jpg", "027eef85-ccc1-4a66-8967-5d74f34c8bb4.jpg", "08f5398d-7f89-47da-a5cd-1ed74967dc1f.jpg", "0fd781ff-ec46-4bdc-a4e8-24f18bf07def.jpg", "0fb4aeee-f949-4c7b-a6d8-05bf0736bdd1.jpg", "6edac66e-c0de-4e69-a9d6-b2e6f6f9001b.jpg", "bfb9e165-c643-4993-9b3a-7e73571672a6.jpg"] # Reset conversation def reset_conversation(): st.session_state.conversation = [] st.session_state.messages = [] # 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("*Generated content may be inaccurate or false.*") st.sidebar.markdown("\n[TypeGPT](https://typegpt.net).") # Initialize previous option and messages 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.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'TypeGPT.net - {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"): try: 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, stream=True, max_tokens=3000, ) response = st.write_stream(stream) except Exception as e: response = ("😵‍💫 Looks like someone unplugged something! " "Either the model space is being updated or something is down. " "Try again later. Here's a random pic of a 🐶:") st.write(response) random_dog_pick = 'https://random.dog/' + random_dog[np.random.randint(len(random_dog))] st.image(random_dog_pick) st.write("This was the error message:") st.write(e) st.session_state.messages.append({"role": "assistant", "content": response}) # import gradio as gr # from huggingface_hub import InferenceClient # """ # For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference # """ # client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") # def respond( # message, # history: list[tuple[str, str]], # system_message, # max_tokens, # temperature, # top_p, # ): # messages = [{"role": "system", "content": system_message}] # for val in history: # if val[0]: # messages.append({"role": "user", "content": val[0]}) # if val[1]: # messages.append({"role": "assistant", "content": val[1]}) # messages.append({"role": "user", "content": message}) # response = "" # for message in client.chat_completion( # messages, # max_tokens=max_tokens, # stream=True, # temperature=temperature, # top_p=top_p, # ): # token = message.choices[0].delta.content # response += token # yield response # """ # For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface # """ # demo = gr.ChatInterface( # respond, # additional_inputs=[ # gr.Textbox(value="You are a friendly Chatbot.", label="System message"), # gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"), # gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"), # gr.Slider( # minimum=0.1, # maximum=1.0, # value=0.95, # step=0.05, # label="Top-p (nucleus sampling)", # ), # ], # ) # if __name__ == "__main__": # demo.launch() ##################################### # import gradio as gr # gr.load("models/meta-llama/Meta-Llama-3.1-70B-Instruct").launch() ######################################## # import streamlit as st # from transformers import AutoTokenizer, AutoModelForCausalLM # # Load model directly # tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct") # model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct") # # Initialize chat history # if "chat_history" not in st.session_state: # st.session_state.chat_history = [] # # Display chat history # for chat in st.session_state.chat_history: # st.write(f"User: {chat['user']}") # st.write(f"Response: {chat['response']}") # # Get user input # user_input = st.text_input("Enter your message:") # # Generate response # if st.button("Send"): # inputs = tokenizer(user_input, return_tensors="pt") # outputs = model.generate(**inputs) # response = tokenizer.decode(outputs[0], skip_special_tokens=True) # st.session_state.chat_history.append({"user": user_input, "response": response}) # st.write(f"Response: {response}")