Instructions to use W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124 with Transformers:

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

pipe = pipeline("text-generation", model="W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124")
model = AutoModelForCausalLM.from_pretrained("W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124", 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 W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124

SGLang

How to use W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124 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 "W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124" \
    --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": "W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124",
		"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 "W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124" \
        --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": "W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124 with Docker Model Runner:
```
docker model run hf.co/W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124
```

llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124

This model is a fine-tuned version of W-61/llama-3-8b-base-sft-ultrachat-8xh200 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

Loss: 0.6357
Beta Dpo/gap Mean: 28.0227
Beta Dpo/gap Std: 50.3673
Beta Dpo/beta Used Raw: 0.0207
Beta Dpo/beta Used: 0.0430
Beta Dpo/mask Keep Frac: 1.0
Logits/chosen: -0.8454
Logits/rejected: -0.8282

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: 4
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Beta Dpo/gap Mean	Beta Dpo/gap Std	Beta Dpo/beta Used Raw	Beta Dpo/beta Used	Beta Dpo/mask Keep Frac	Logits/chosen	Logits/rejected
5.1899	0.4188	200	0.6122	23.1744	48.2593	0.0140	0.0346	1.0	-0.8157	-0.8025
3.5281	0.8377	400	0.6357	28.0227	50.3673	0.0207	0.0430	1.0	-0.8454	-0.8282

Framework versions

Transformers 4.51.0
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.21.4

Downloads last month: 11

Safetensors

Model size

8B params

Tensor type

F32

Model tree for W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124

Base model

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

Finetuned

W-61/llama-3-8b-base-sft-ultrachat-8xh200

Finetuned

(70)

this model

W-61
/

llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124

llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124

Dataset used to train W-61/llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124