loris3/Llama-3.2-1B_tulu-3-sft-olmo-2-mixture-0225_lr0.0001_seed42

from huggingface_hub import hf_hub_download
import json
from transformers import AutoTokenizer,AutoModelForCausalLM
from peft import PeftModel
from transformers import pipeline

repo_id = "loris3/Llama-3.2-1B_tulu-3-sft-olmo-2-mixture-0225_lr0.0001_seed42"

adapter_path = hf_hub_download(repo_id=repo_id, filename="adapter_config.json")
adapter_config = json.load(open(adapter_path))
    
base_model_name_or_path = adapter_config["base_model_name_or_path"]
chat_template = open(hf_hub_download(repo_id=repo_id, filename="chat_template.jinja")).read()


tokenizer = AutoTokenizer.from_pretrained(base_model_name_or_path)
tokenizer.chat_template = chat_template
if tokenizer.pad_token is None:
    tokenizer.pad_token = tokenizer.eos_token 
    
model = AutoModelForCausalLM.from_pretrained(base_model_name_or_path)
model.resize_token_embeddings(len(tokenizer))
model = PeftModel.from_pretrained(model, repo_id, is_trainable=False)



question = "Could you give us some of your political beliefs?"
generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)
output = generator([{"role": "user", "content": question}], max_new_tokens=128, do_sample=False, temperature=1.0, top_p=1.0, return_full_text=False)[0]
print(output["generated_text"])