File size: 2,343 Bytes
a25c1ff c49c1a9 9c95f36 c49c1a9 9c95f36 c49c1a9 ace2f35 0f3f2f2 c49c1a9 ace2f35 c49c1a9 ace2f35 c49c1a9 ace2f35 c49c1a9 |
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 |
import gradio as gr
import os
from pathlib import Path
import argparse
from huggingface_hub import snapshot_download
# repo_name = "TheBloke/Mistral-7B-v0.1-GGUF"
# model_file = "mistral-7b-v0.1.Q6_K.gguf"
#repo_name = 'HumanityFTW/so_rude'
#model_file = "mistral-comedy-2.0-ckpt-600.Q6_K.gguf"
repo_name = 'TheBloke/OpenHermes-2.5-Mistral-7B-GGUF'
model_file = "openhermes-2.5-mistral-7b.Q4_K_M.gguf"
print('Fetching model:', repo_name, model_file)
snapshot_download(repo_id=repo_name, local_dir=".", allow_patterns=model_file)
print('Done fetching model:')
DEFAULT_MODEL_PATH = model_file
from llama_cpp import Llama
llm = Llama(model_path=model_file, model_type="mistral")
def predict(input, chatbot, max_length, top_p, temperature, history):
chatbot.append((input, ""))
response = ""
history.append(input)
for output in llm(input, stream=True, temperature=temperature, top_p=top_p, max_tokens=max_length, ):
piece = output['choices'][0]['text']
response += piece
chatbot[-1] = (chatbot[-1][0], response)
yield chatbot, history
history.append(response)
yield chatbot, history
def reset_user_input():
return gr.update(value="")
def reset_state():
return [], []
with gr.Blocks() as demo:
gr.HTML("""<h1 align="center">So Rude</h1>""")
chatbot = gr.Chatbot()
with gr.Row():
with gr.Column(scale=4):
user_input = gr.Textbox(show_label=False, placeholder="Input...", lines=8, elem_id="user_input")
submitBtn = gr.Button("Submit", variant="primary", elem_id="submit_btn")
with gr.Column(scale=1):
max_length = gr.Slider(0, 256, value=64, step=1.0, label="Maximum Length", interactive=True)
top_p = gr.Slider(0, 1, value=0.7, step=0.01, label="Top P", interactive=True)
temperature = gr.Slider(0, 2.0, value=0.95, step=0.01, label="Temperature", interactive=True)
emptyBtn = gr.Button("Clear History")
history = gr.State([])
submitBtn.click(
predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history], show_progress=True
)
submitBtn.click(reset_user_input, [], [user_input])
emptyBtn.click(reset_state, outputs=[chatbot, history], show_progress=True)
demo.queue().launch(share=False, inbrowser=True) |