Instructions to use W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315 with Transformers:

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

pipe = pipeline("text-generation", model="W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315")
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-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315")
model = AutoModelForCausalLM.from_pretrained("W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315", 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-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315 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-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315"
# 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-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315

SGLang

How to use W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315 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-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315" \
    --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-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315",
		"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-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315" \
        --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-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315 with Docker Model Runner:
```
docker model run hf.co/W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315
```

qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315 / README.md

W-61

Upload validated Qwen3 ultrafeedback Margin-DPO checkpoint for qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315

8b543b5 verified 4 months ago

preview code

Raw

History Blame Contribute Delete

2.77 kB

	---
	library_name: transformers
	base_model: W-61/qwen3-8b-base-sft-ultrachat-4xh200-batch-128
	tags:
	- alignment-handbook
	- margin-dpo
	- generated_from_trainer
	datasets:
	- HuggingFaceH4/ultrafeedback_binarized
	model-index:
	- name: qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315

	This model is a fine-tuned version of [W-61/qwen3-8b-base-sft-ultrachat-4xh200-batch-128](https://huggingface.co/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: 0.5602
	- Margin Dpo/margin Mean: 48.7131
	- Margin Dpo/margin Std: 68.1546
	- Logps/chosen: -316.0414
	- Logps/rejected: -345.1451
	- Logps/ref Chosen: -281.4589
	- Logps/ref Rejected: -261.8495
	- Logits/chosen: 1.1933
	- Logits/rejected: 1.2367

	## 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 \| Margin Dpo/margin Mean \| Margin Dpo/margin Std \| Logps/chosen \| Logps/rejected \| Logps/ref Chosen \| Logps/ref Rejected \| Logits/chosen \| Logits/rejected \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|:----------------------:\|:---------------------:\|:------------:\|:--------------:\|:----------------:\|:------------------:\|:-------------:\|:---------------:\|
	\| 4.9383 \| 0.4188 \| 200 \| 0.5970 \| 28.2584 \| 39.0244 \| -287.0227 \| -295.6718 \| -281.4589 \| -261.8495 \| 1.4300 \| 1.4697 \|
	\| 4.2739 \| 0.8377 \| 400 \| 0.5602 \| 48.7131 \| 68.1546 \| -316.0414 \| -345.1451 \| -281.4589 \| -261.8495 \| 1.1933 \| 1.2367 \|


	### Framework versions

	- Transformers 4.51.0
	- Pytorch 2.3.1+cu121
	- Datasets 2.21.0
	- Tokenizers 0.21.4