Instructions to use Junrulu/Llama-3-8B-Instruct-Iterative-SamPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Junrulu/Llama-3-8B-Instruct-Iterative-SamPO with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Junrulu/Llama-3-8B-Instruct-Iterative-SamPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Junrulu/Llama-3-8B-Instruct-Iterative-SamPO")
model = AutoModelForCausalLM.from_pretrained("Junrulu/Llama-3-8B-Instruct-Iterative-SamPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Junrulu/Llama-3-8B-Instruct-Iterative-SamPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Junrulu/Llama-3-8B-Instruct-Iterative-SamPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Junrulu/Llama-3-8B-Instruct-Iterative-SamPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Junrulu/Llama-3-8B-Instruct-Iterative-SamPO

SGLang

How to use Junrulu/Llama-3-8B-Instruct-Iterative-SamPO with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Junrulu/Llama-3-8B-Instruct-Iterative-SamPO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Junrulu/Llama-3-8B-Instruct-Iterative-SamPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Junrulu/Llama-3-8B-Instruct-Iterative-SamPO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Junrulu/Llama-3-8B-Instruct-Iterative-SamPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Junrulu/Llama-3-8B-Instruct-Iterative-SamPO with Docker Model Runner:
```
docker model run hf.co/Junrulu/Llama-3-8B-Instruct-Iterative-SamPO
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Llama-3-8B-Instruct-Iterative-SamPO

This repository provides a fine-tuned version of Llama-3-8B-Instruct, using our proposed SamPO algorithm: Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence. We obey all licenses mentioned in llama3's work.

Performance

Model	GSM8K	IFEval	PiQA	MMLU	TruthfulQA	AlpacaEval2	LC AlpacaEval2	Length in Tokens
Llama3-8B-Instruct	75.06	49.40	80.69	63.85	36.47	22.57	22.92	421
Llama3-8B-Instruct-DPO	75.59	51.80	81.94	64.06	40.39	23.34	23.20	422
Llama3-8B-Instruct-Iterative-DPO	74.91	52.52	81.66	64.02	39.90	23.92	25.50	403
Llama3-8B-Instruct-Iterative-SamPO	77.81	60.55	81.18	64.12	44.07	30.68	35.14	377

Evaluation Details

Five conditional benchmarks, using lm-evaluation-harness:

GSM8K: 8-shot, report strict match
IFEval: 3-shot, report instruction-level strict accuracy
PiQA: 3-shot, report accuracy
MMLU: 0-shot, report normalized accuracy
TruthfulQA: 3-shot, report accuracy of single-true mc1 setting

One open-ended benchmark, using official alpaca_eval:

AlpacaEval2: win rate (%) judged by GPT-4-turbo between the model's outputs vs. the GPT-4-turbo's response
LC AlpacaEval2: length-debiased win rate (%) of AlpacaEval2
Length in Tokens: the average output length of AlpacaEval2, calculated in tokens with Llama3's tokenizer

Input Format

The model is trained to use the following format:

<|start_header_id|>user<|end_header_id|>

{PROMPT}<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>

{Response}

Training hyperparameters

The following hyperparameters were used during DPO/SamPO training:

DPO beta: 0.1
learning_rate: 4e-7
total_train_batch_size: 128
optimizer: AdamW with beta1 0.9, beta2 0.999 and epsilon 1e-8
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
Weight Decay: 0.0
num_epochs: 3.0
Specifically add above input format over training samples

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

F16

Model tree for Junrulu/Llama-3-8B-Instruct-Iterative-SamPO

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Finetuned

(1118)

this model

Quantizations

1 model

Dataset used to train Junrulu/Llama-3-8B-Instruct-Iterative-SamPO

Collection including Junrulu/Llama-3-8B-Instruct-Iterative-SamPO

SamPO

Collection

Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence • 4 items • Updated Oct 18, 2024 • 1