Spaces:
Runtime error
Runtime error
File size: 2,458 Bytes
6ed0fd3 8b99594 d86d51d d5bcccc 6ed0fd3 678e600 d86d51d 6ef7550 52e27c2 2589510 1719f05 d86d51d c588f84 d5bcccc d86d51d 8b99594 d86d51d 6ed0fd3 d86d51d 6ed0fd3 d86d51d 6ed0fd3 d86d51d 6ed0fd3 |
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 |
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, BitsAndBytesConfig
from peft import PeftModel
import torch
import os
"""
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
"""
# Set your model and adapter paths
API_KEY = os.environ.get("llama_ACCESS_TOKEN")
BASE_MODEL = "meta-llama/Meta-Llama-3-8B"
PEFT_ADAPTER = "asdc/Llama-3-8B-multilingual-temporal-expression-normalization"
tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, token=API_KEY)
base_model = AutoModelForCausalLM.from_pretrained(
BASE_MODEL,
torch_dtype=torch.float16,
device_map="auto",
token=API_KEY
)
nf4_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16
)
model = PeftModel.from_pretrained(base_model, PEFT_ADAPTER, token=API_KEY, quantization_config=nf4_config)
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
device_map="auto"
)
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
prompt = system_message + "\n"
for user, assistant in history:
if user:
prompt += f"User: {user}\n"
if assistant:
prompt += f"Assistant: {assistant}\n"
prompt += f"User: {message}\nAssistant:"
outputs = pipe(
prompt,
max_new_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
do_sample=True,
pad_token_id=tokenizer.eos_token_id,
)
response = outputs[0]["generated_text"][len(prompt):]
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()
|