Instructions to use OpenRLHF/Llama-3-8b-iter-dpo-179k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenRLHF/Llama-3-8b-iter-dpo-179k with Transformers:

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

pipe = pipeline("text-generation", model="OpenRLHF/Llama-3-8b-iter-dpo-179k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenRLHF/Llama-3-8b-iter-dpo-179k")
model = AutoModelForCausalLM.from_pretrained("OpenRLHF/Llama-3-8b-iter-dpo-179k")
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

vLLM

How to use OpenRLHF/Llama-3-8b-iter-dpo-179k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenRLHF/Llama-3-8b-iter-dpo-179k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenRLHF/Llama-3-8b-iter-dpo-179k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenRLHF/Llama-3-8b-iter-dpo-179k

SGLang

How to use OpenRLHF/Llama-3-8b-iter-dpo-179k 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 "OpenRLHF/Llama-3-8b-iter-dpo-179k" \
    --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": "OpenRLHF/Llama-3-8b-iter-dpo-179k",
		"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 "OpenRLHF/Llama-3-8b-iter-dpo-179k" \
        --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": "OpenRLHF/Llama-3-8b-iter-dpo-179k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenRLHF/Llama-3-8b-iter-dpo-179k with Docker Model Runner:
```
docker model run hf.co/OpenRLHF/Llama-3-8b-iter-dpo-179k
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

This model is trained with Iterative DPO in OpenRLHF

Datasets and Hyperparameters

Reward Model:https://huggingface.co/OpenLLMAI/Llama-3-8b-rm-700k
SFT Model: https://huggingface.co/OpenLLMAI/Llama-3-8b-sft-mixture
Prompt Dataset: https://huggingface.co/datasets/OpenLLMAI/prompt-collection-v0.1

Max Prompt Length: 2048
Max Response Length: 2048
best_of_n: 2 (2 samples for each prompt)
Learning Rate: 5e-7
Beta: 0.1
Scheduler: Cosine with Warmup (0.03) and MinLR (0.1 * init_lr)
Rollout Batch Size: 20000
Training Batch Size: 256
Number of Iterations: 9

Evaluation

########## First turn ##########
                      score
model           turn
Llama3-iter-dpo 1      8.55
########## Second turn ##########
                        score
model           turn
Llama3-iter-dpo 2     7.95625
########## Average ##########
                    score
model
Llama3-iter-dpo  8.253125
Llama3-sft-baseline 7.69

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

BF16