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"])

Training procedure

Visualize in Weights & Biases

Training Hyperparameters

Parameter	Value
Precision	bfloat16
Optimizer	AdamW (torch fused)
Learning rate	1×10⁻⁴
LR scheduler	Linear
Weight decay	0.0
Max grad norm	1.0
LoRA rank (r)	16
LoRA alpha	32
LoRA dropout	0.1
LoRA bias	none
Target modules	q_proj, k_proj, v_proj, o_proj
Trainable params	LoRA only
Train batch size / device	4
Gradient accumulation	8
Effective batch size	32
Training epochs	1
Max sequence length	1024
Gradient checkpointing	False
Seed	42

Framework versions

PEFT 0.17.1
TRL: 0.23.0
Transformers: 4.56.2
Pytorch: 2.8.0+cu126
Datasets: 4.0.0
Tokenizers: 0.22.1

Evaluation

We evaluate with OLMES

Task suites: core_9mcqa::olmes, mmlu:mc::olmes, olmo_2_generative::olmes, olmo_2_heldout::olmes

Task	Score
AGIEval	0.24
ARC_C	0.38
ARC_E	0.60
BBH	0.32
BoolQ	0.67
CSQA	0.50
CoQA	0.65
DROP	0.25
GSM8K	0.08
HSwag	0.53
JPRDY	0.53
MMLU	0.30
MMLU-Pro	0.16
NatQs	0.16
OBQA	0.39
PIQA	0.67
SIQA	0.47
SQuAD	0.73
TriviaQA	0.48
WinoG	0.58