File size: 2,074 Bytes
eceedce e0ecae1 eceedce e0ecae1 eceedce e0ecae1 eceedce e0ecae1 eceedce e0ecae1 eceedce e0ecae1 eceedce |
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 |
import gradio as gr
from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer, Trainer, TrainingArguments
# Load the dataset
dataset = load_dataset("json", data_files="dataset.jsonl")
# Load the pre-trained model and tokenizer
model_name = "Salesforce/codegen-2B-multi"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Tokenize the dataset
def tokenize_function(examples):
return tokenizer(examples["input"], text_target=examples["output"], truncation=True)
tokenized_dataset = dataset.map(tokenize_function, batched=True)
# Define training arguments
training_args = TrainingArguments(
output_dir="./results",
overwrite_output_dir=True,
evaluation_strategy="epoch",
learning_rate=5e-5,
per_device_train_batch_size=2,
num_train_epochs=3,
save_strategy="epoch",
logging_dir="./logs",
logging_strategy="epoch",
)
# Trainer setup
trainer = Trainer(
model=model,
args=training_args,
train_dataset=tokenized_dataset["train"],
eval_dataset=tokenized_dataset["train"],
)
# Train the model
trainer.train()
# Save the fine-tuned model
trainer.save_model("./fine_tuned_model")
tokenizer.save_pretrained("./fine_tuned_model")
# Load the fine-tuned model for inference
fine_tuned_model = AutoModelForCausalLM.from_pretrained("./fine_tuned_model")
fine_tuned_tokenizer = AutoTokenizer.from_pretrained("./fine_tuned_model")
# Define a Gradio interface for testing the model
def generate_cypress_code(prompt):
inputs = fine_tuned_tokenizer(prompt, return_tensors="pt")
outputs = fine_tuned_model.generate(inputs["input_ids"], max_length=150, num_return_sequences=1)
return fine_tuned_tokenizer.decode(outputs[0], skip_special_tokens=True)
# Launch the Gradio interface
interface = gr.Interface(
fn=generate_cypress_code,
inputs="text",
outputs="text",
title="Cypress Test Generator",
description="Enter a description of the test you want to generate Cypress code for.",
)
interface.launch() |