Spaces:
Running
Running
File size: 2,565 Bytes
6bcba58 5103369 6bcba58 8d3dea1 6bcba58 6b02e11 6bcba58 84ef11d 2932ae3 6bcba58 84ef11d 6bcba58 84ef11d 6bcba58 2932ae3 6bcba58 d1dac8f 6bcba58 d1dac8f 84ef11d d64eb6a c48827c 6bcba58 84ef11d 6bcba58 84ef11d |
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 |
import gradio as gr
import os
import spaces
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
from threading import Thread
# Set an environment variable
HF_TOKEN = os.environ.get("HF_TOKEN", None)
DESCRIPTION = '''
<div>
<h1 style="text-align: center;">Mistral 7B Instruct v0.3</h1>
</div>
'''
# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3", device_map="auto")
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
@spaces.GPU(duration=120)
def chat_mistral7b_v0dot3(message: str,
history: list,
temperature: float,
max_new_tokens: int
) -> str:
"""
Generate a streaming response using the mistralai/Mistral-7B-Instruct-v0.3 model.
Args:
message (str): The input message.
history (list): The conversation history used by ChatInterface.
temperature (float): The temperature for generating the response.
max_new_tokens (int): The maximum number of new tokens to generate.
Returns:
str: The generated response.
"""
conversation = []
for user, assistant in 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").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,
temperature=temperature,
eos_token_id=terminators,
)
# This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.
if temperature == 0:
generate_kwargs['do_sample'] = False
t = Thread(target=model.generate, kwargs=generate_kwargs)
t.start()
outputs = []
for text in streamer:
outputs.append(text)
yield "".join(outputs)
with gr.Blocks() as demo:
gr.Interface(
fn=chat_mistral7b_v0dot3,
inputs=[gr.Textbox(), gr.Textbox(), gr.Number(), gr.Number()],
outputs=[gr.Textbox()]
)
if __name__ == "__main__":
demo.launch() |