File size: 1,562 Bytes
26b9c2e e7bae5d 26b9c2e 67158a0 26b9c2e 67158a0 26b9c2e e7bae5d 26b9c2e |
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 |
# import gradio as gr
# gr.load("models/Artigenz/Artigenz-Coder-DS-6.7B").launch()
import gradio as gr
import transformers
# Load the model and tokenizer
model_name = "Artigenz/Artigenz-Coder-DS-6.7B"
tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
model = transformers.AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto")
max_new_tokens:int=1024
do_sample:bool=True
num_beams:int=1
temperature:float=0.5
top_p:float=0.95
top_k:float=40
repetition_penalty:float=1.1
pipe = transformers.pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=max_new_tokens,
do_sample=do_sample,
num_beams=num_beams,
temperature=temperature,
top_p=top_p,
top_k=top_k,
repetition_penalty=repetition_penalty,
)
def generate_response(input_text):
messages = [
{
"role": "system", "content": "You are a helpful coding chatbot. You will answer the user's questions to the best of your ability.",
"role": "user", "content": input_text,
},
]
return pipe(messages)[0]['generated_text'][-1]['content'].replace("\\n", "\n")
# Define the Gradio interface
iface = gr.Interface(
fn=generate_response,
inputs="text",
outputs="text",
title="Artigenz Coder - 6.7B Model",
description="A code-generation model from Artigenz. Enter a prompt to get code suggestions or completions."
)
# Launch the interface
iface.launch()
|