Created
April 27, 2024 06:51
-
-
Save mzbac/c10ba6b8cad89942c8924a27e82a1455 to your computer and use it in GitHub Desktop.
preprocess.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments,BitsAndBytesConfig | |
from datasets import load_dataset | |
model_name ="meta-llama/Meta-Llama-3-8B-Instruct" | |
tokenizer = AutoTokenizer.from_pretrained(model_name) | |
dataset = load_dataset("glaiveai/glaive-function-calling-v2",split="train") | |
def formatting_prompts_func(example): | |
output_texts = [] | |
for i in range(len(example['system'])): | |
messages = [ | |
{ | |
"role": "system", | |
"content": example['system'][i][len("SYSTEM:"):].strip(), | |
}, | |
] | |
conversations = example['chat'][i].split("<|endoftext|>") | |
for message in conversations: | |
message = message.strip() | |
if message: | |
if "USER:" in message: | |
user_content = message.split("ASSISTANT:")[0].strip() | |
messages.append({"role": "user", "content": user_content[5:].strip()}) | |
if "ASSISTANT:" in message: | |
assistant_content = message.split("ASSISTANT:")[1].strip() | |
messages.append({"role": "assistant", "content": assistant_content}) | |
elif message.startswith("FUNCTION RESPONSE:"): | |
function_response = message[18:].strip() | |
if "ASSISTANT:" in function_response: | |
function_content, assistant_content = function_response.split("ASSISTANT:") | |
messages.append({"role": "user", "content": function_content.strip()}) | |
messages.append({"role": "assistant", "content": assistant_content.strip()}) | |
else: | |
messages.append({"role": "user", "content": function_response}) | |
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=False) | |
output_texts.append(text) | |
return {"text": output_texts} | |
dataset = dataset.map(formatting_prompts_func, batched=True) | |
dataset = dataset.remove_columns(["system", "chat"]) | |
dataset.push_to_hub("mzbac/glaive-function-calling-v2-llama-3-format") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment