Spaces:
Runtime error
Runtime error
File size: 3,222 Bytes
65ecc4c |
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 |
import gradio as gr
from langchain.llms import LlamaCpp
from langchain.prompts import PromptTemplate
from langchain.chains import LLMChain
from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from huggingface_hub import hf_hub_download
callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
repo_id="TheBloke/Mistral-7B-OpenOrca-GGUF"
model_name="mistral-7b-openorca.Q5_K_M.gguf"
hf_hub_download(repo_id=repo_id,
filename=model_name,local_dir =".")
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, top_p=0.95,
):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
formatted_prompt = format_prompt(prompt, history)
llm = LlamaCpp(
model_path=model_name,
temperature=temperature,
max_tokens=2000,
top_p=top_p,
callback_manager=callback_manager,
verbose=True, # Verbose is required to pass to the callback manager
)
# stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
output = ""
output=llm(formatted_prompt)
# for response in stream:
# output += response.token.text
# yield output
return output
additional_inputs=[
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",
)
]
css = """
#mkd {
height: 500px;
overflow: auto;
border: 1px solid #ccc;
}
"""
with gr.Blocks(css=css) as demo:
gr.HTML("<h1><center>Mistral 7B Instruct<h1><center>")
gr.HTML("<h3><center>In this demo, you can chat with <a href='https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1'>Mistral-7B-Instruct</a> model. 💬<h3><center>")
gr.HTML("<h3><center>Learn more about the model <a href='https://huggingface.co/docs/transformers/main/model_doc/mistral'>here</a>. 📚<h3><center>")
gr.ChatInterface(
generate,
additional_inputs=additional_inputs,
examples=[["What is the secret to life?"], ["Write me a recipe for pancakes."]]
)
demo.queue().launch(debug=True) |