This model was requested for further testing. Original thread
Code example
from transformers import AutoModelForCausalLM, AutoTokenizer
def generate_response(prompt):
"""
Generate a response from the model based on the input prompt.
Args:
prompt (str): Prompt for the model.
Returns:
str: The generated response from the model.
"""
# Tokenize the input prompt
inputs = tokenizer(prompt, return_tensors="pt")
# Generate output tokens
outputs = model.generate(**inputs, max_new_tokens=256, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.pad_token_id)
# Decode the generated tokens to a string
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
return response
# Load the model and tokenizer
model_id = "macadeliccc/KunoichiLake-2x7b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True)
prompt = "Write a quicksort algorithm in python"
# Generate and print responses for each language
print("Response:")
print(generate_response(prompt), "\n")