File size: 4,683 Bytes
992ad15 2ae746c b8c846d b8599dd 2ae746c 81c62e1 2ae746c 992ad15 2ae746c 992ad15 2ae746c 992ad15 |
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 |
#!/usr/bin/env python#
from llama_cpp import Llama
from time import time
import gradio as gr
import psutil
# Initing things
print("debug: init model")
#llm = Llama(model_path="./model.bin") # LLaMa model
llama_model_name = "TheBloke/dolphin-2.2.1-AshhLimaRP-Mistral-7B-GGUF"
print("! INITING DONE !")
# Preparing things to work
title = "Demo for 7B Models - Quantized"
desc = '''<h1>Demo for 7B Models - Quantized</h1>
Quantized to run in the free tier hosting.
Have a quick way to test models or share them with others without hassle.
It runs slow, as it's on cpu. Usable for basic tests.
It uses quantized models in gguf-Format and llama.cpp to run them.
<br>''' + f"DEBUG: Memory used: {psutil.virtual_memory()[2]}<br>" + '''
Powered by ...'''
import os
from threading import Thread
from typing import Iterator
import gradio as gr
import spaces
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
DESCRIPTION = "# Mistral-7B"
if torch.cuda.is_available():
DESCRIPTION += "\n<p>This space is optimized for CPU only. Use another one if you want to go fast and use GPU. </p>"
MAX_MAX_NEW_TOKENS = 2048
DEFAULT_MAX_NEW_TOKENS = 1024
MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
#download model here
# check localstorage, if no there, load, else use existing.
if torch.cuda.is_available():
model_id = "mistralai/Mistral-7B-Instruct-v0.1"
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_id)
def generate(
message: str,
chat_history: list[tuple[str, str]],
max_new_tokens: int = 1024,
temperature: float = 0.6,
top_p: float = 0.9,
top_k: int = 50,
repetition_penalty: float = 1.2,
) -> Iterator[str]:
conversation = []
for user, assistant in chat_history:
conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
conversation.append({"role": "user", "content": message})
input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
input_ids = input_ids.to(model.device)
streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
generate_kwargs = dict(
{"input_ids": input_ids},
streamer=streamer,
max_new_tokens=max_new_tokens,
do_sample=True,
top_p=top_p,
top_k=top_k,
temperature=temperature,
num_beams=1,
repetition_penalty=repetition_penalty,
)
t = Thread(target=model.generate, kwargs=generate_kwargs)
t.start()
outputs = []
for text in streamer:
outputs.append(text)
yield "".join(outputs)
chat_interface = gr.ChatInterface(
fn=generate,
additional_inputs=[
gr.Slider(
label="Max new tokens",
minimum=1,
maximum=MAX_MAX_NEW_TOKENS,
step=1,
value=DEFAULT_MAX_NEW_TOKENS,
),
gr.Slider(
label="Temperature",
minimum=0.1,
maximum=4.0,
step=0.1,
value=0.6,
),
gr.Slider(
label="Top-p (nucleus sampling)",
minimum=0.05,
maximum=1.0,
step=0.05,
value=0.9,
),
gr.Slider(
label="Top-k",
minimum=1,
maximum=1000,
step=1,
value=50,
),
gr.Slider(
label="Repetition penalty",
minimum=1.0,
maximum=2.0,
step=0.05,
value=1.2,
),
],
stop_btn=None,
examples=[
["Hello there! How are you doing?"],
["Can you explain briefly to me what is the Python programming language?"],
["Explain the plot of Cinderella in a sentence."],
["How many hours does it take a man to eat a Helicopter?"],
["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
],
)
with gr.Blocks(css="style.css") as demo:
gr.Markdown(DESCRIPTION)
gr.DuplicateButton(
value="Duplicate Space for private use",
elem_id="duplicate-button",
visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
)
chat_interface.render()
if __name__ == "__main__":
demo.queue(max_size=20).launch() |