hipnologo/falcon-7b-qlora-finetune-chatbot

# Import necessary classes and functions
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftConfig, PeftModel

# Specify the model
PEFT_MODEL = "hipnologo/falcon-7b-qlora-finetune-chatbot"

# Load the PEFT config
config = PeftConfig.from_pretrained(PEFT_MODEL)

# Load the base model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    config.based_model_name_or_path,
    return_dict=True,
    quantization_config=bnb_config,
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)

# Set the padding token to be the same as the EOS token
tokenizer.pad_token = tokenizer.eos_token

# Load the PEFT model
model = PeftModel.from_pretrained(model, PEFT_MODEL)

# Set the generation parameters
generation_config = model.generation_config
generation_config.max_new_tokens = 200
generation_config.temperature = 0.7
generation_config.top_p = 0.7
generation_config.num_return_sequences = 1
generation_config.pad_token_id = tokenizer.eos_token_id
generation_config.eos_token_id = tokenizer.eos_token_id

# Define the prompt
prompt = """
<human>: How can I create an account?
<assistant>:
""".strip()
print(prompt)

# Encode the prompt
encoding = tokenizer(prompt, return_tensors="pt").to(model.device)

# Generate a response
with torch.inference_mode():
  outputs = model.generate(
      input_ids=encoding.input_ids,
      attention_mask=encoding.attention_mask,
      generation_config=generation_config,
  )

# Print the generated response
print(tokenizer.decode(outputs[0],skip_special_tokens=True))