Last active
May 9, 2024 00:35
-
-
Save mzbac/b12f322dbeb7c9ef229d10b18d509951 to your computer and use it in GitHub Desktop.
glaiveai/glaive-function-calling-v2 clean up
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 | |
import json | |
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 cleanup(input_string): | |
arguments_index = input_string.find('"arguments"') | |
if arguments_index == -1: | |
return input_string | |
start_quote = input_string.find("'", arguments_index) | |
if start_quote == -1: | |
return input_string | |
end_quote = input_string.rfind("'") | |
if end_quote == -1 or end_quote <= start_quote: | |
return input_string | |
arguments_value = input_string[start_quote+1:end_quote] | |
output_string = input_string[:start_quote] + arguments_value + input_string[end_quote+1:] | |
return output_string | |
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: | |
continue_outer = False | |
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() | |
if "<functioncall>" in assistant_content: | |
text = assistant_content.replace("<functioncall>","").strip() | |
json_str = cleanup(text) | |
try: | |
data = json.loads(json_str) | |
except json.JSONDecodeError as e: | |
print(f"0 - Failed to decode JSON: {json_str} - {assistant_content}") | |
continue_outer = True | |
break | |
new_func_text = "<functioncall> "+ json_str | |
messages.append({"role": "assistant", "content": new_func_text}) | |
else: | |
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:") | |
try: | |
data = json.loads(function_content.strip()) | |
except json.JSONDecodeError as e: | |
print(f"1 - Failed to decode JSON: {function_content}") | |
continue_outer = True | |
break | |
messages.append({"role": "user", "content": function_content.strip()}) | |
messages.append({"role": "assistant", "content": assistant_content.strip()}) | |
else: | |
try: | |
data = json.loads(function_response.strip()) | |
except json.JSONDecodeError as e: | |
print(f"2 - Failed to decode JSON: {function_response}") | |
continue_outer = True | |
break | |
messages.append({"role": "user", "content": function_response.strip()}) | |
elif message.startswith("ASSISTANT:"): | |
assistant_content = message.split("ASSISTANT:")[1].strip() | |
if "<functioncall>" in assistant_content: | |
text = assistant_content.replace("<functioncall>","").strip() | |
json_str = cleanup(text) | |
try: | |
data = json.loads(json_str) | |
except json.JSONDecodeError as e: | |
print(f"3 - Failed to decode JSON: {json_str} - {assistant_content}") | |
continue_outer = True | |
break | |
new_func_text = "<functioncall> "+ json_str | |
messages.append({"role": "assistant", "content": new_func_text}) | |
if continue_outer: | |
continue | |
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=False) | |
output_texts.append(text) | |
del example['system'] | |
del example['chat'] | |
return {"text": output_texts} | |
dataset = dataset.map(formatting_prompts_func, batched=True) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment