Instructions to use W-61/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use W-61/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855 with Transformers:

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

pipe = pipeline("text-generation", model="W-61/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("W-61/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855")
model = AutoModelForCausalLM.from_pretrained("W-61/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855", 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/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "W-61/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855"
# 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/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/W-61/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855

SGLang

How to use W-61/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855 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/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855" \
    --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/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855",
		"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/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855" \
        --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/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use W-61/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855 with Docker Model Runner:
```
docker model run hf.co/W-61/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855
```

qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855

This model is a fine-tuned version of W-61/qwen3-8b-base-sft-ultrachat-4xh200-batch-128 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

Loss: 0.5512
R Dpo/chosen Len: 294.4800
R Dpo/rejected Len: 249.8700
R Dpo/length Delta: 44.6100
R Dpo/regularization Term: 0.0
Logps/chosen: -313.3703
Logps/rejected: -344.1740
Logps/ref Chosen: -281.4589
Logps/ref Rejected: -261.8495
Logits/chosen: 1.5782
Logits/rejected: 1.6653

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	R Dpo/chosen Len	R Dpo/rejected Len	R Dpo/length Delta	R Dpo/regularization Term	Logps/chosen	Logps/rejected	Logps/ref Chosen	Logps/ref Rejected	Logits/chosen	Logits/rejected
4.8113	0.4188	200	0.5963	294.4800	249.8700	44.6100	0.0	-288.0062	-296.9761	-281.4589	-261.8495	1.4237	1.4639
4.3796	0.8377	400	0.5512	294.4800	249.8700	44.6100	0.0	-313.3703	-344.1740	-281.4589	-261.8495	1.5782	1.6653

Framework versions

Transformers 4.51.0
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.21.4

Downloads last month: 7

Safetensors

Model size

8B params

Tensor type

F32

W-61
/

qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855

qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Dataset used to train W-61/qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855