Instructions to use oxford-llms/llama3-1-ox-llms-8b-dpo-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oxford-llms/llama3-1-ox-llms-8b-dpo-full with Transformers:

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

pipe = pipeline("text-generation", model="oxford-llms/llama3-1-ox-llms-8b-dpo-full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("oxford-llms/llama3-1-ox-llms-8b-dpo-full")
model = AutoModelForCausalLM.from_pretrained("oxford-llms/llama3-1-ox-llms-8b-dpo-full", device_map="auto")
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 oxford-llms/llama3-1-ox-llms-8b-dpo-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oxford-llms/llama3-1-ox-llms-8b-dpo-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oxford-llms/llama3-1-ox-llms-8b-dpo-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/oxford-llms/llama3-1-ox-llms-8b-dpo-full

SGLang

How to use oxford-llms/llama3-1-ox-llms-8b-dpo-full 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 "oxford-llms/llama3-1-ox-llms-8b-dpo-full" \
    --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": "oxford-llms/llama3-1-ox-llms-8b-dpo-full",
		"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 "oxford-llms/llama3-1-ox-llms-8b-dpo-full" \
        --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": "oxford-llms/llama3-1-ox-llms-8b-dpo-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use oxford-llms/llama3-1-ox-llms-8b-dpo-full with Docker Model Runner:
```
docker model run hf.co/oxford-llms/llama3-1-ox-llms-8b-dpo-full
```

llama3-1-ox-llms-8b-dpo-full

This model is a fine-tuned version of oxford-llms/llama3-1-ox-llms-8b-sft-full on the argilla/dpo-mix-7k dataset. It achieves the following results on the evaluation set:

Loss: 0.4831
Rewards/chosen: -0.2543
Rewards/rejected: -1.0940
Rewards/accuracies: 0.7708
Rewards/margins: 0.8397
Logps/rejected: -340.3136
Logps/chosen: -325.1967
Logits/rejected: -1.3101
Logits/chosen: -1.3085

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 64
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.528	0.9479	100	0.5267	-0.0255	-0.6055	0.7604	0.5800	-330.5430	-320.6201	-1.3169	-1.3159
0.3731	1.8957	200	0.4821	-0.2481	-1.0900	0.7604	0.8419	-340.2323	-325.0733	-1.3099	-1.3082