Instructions to use sathiiiii/polyalign-qwen2.5-3b-en-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sathiiiii/polyalign-qwen2.5-3b-en-dpo with Transformers:

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

pipe = pipeline("text-generation", model="sathiiiii/polyalign-qwen2.5-3b-en-dpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sathiiiii/polyalign-qwen2.5-3b-en-dpo")
model = AutoModelForCausalLM.from_pretrained("sathiiiii/polyalign-qwen2.5-3b-en-dpo", 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 sathiiiii/polyalign-qwen2.5-3b-en-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sathiiiii/polyalign-qwen2.5-3b-en-dpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sathiiiii/polyalign-qwen2.5-3b-en-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sathiiiii/polyalign-qwen2.5-3b-en-dpo

SGLang

How to use sathiiiii/polyalign-qwen2.5-3b-en-dpo 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 "sathiiiii/polyalign-qwen2.5-3b-en-dpo" \
    --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": "sathiiiii/polyalign-qwen2.5-3b-en-dpo",
		"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 "sathiiiii/polyalign-qwen2.5-3b-en-dpo" \
        --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": "sathiiiii/polyalign-qwen2.5-3b-en-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sathiiiii/polyalign-qwen2.5-3b-en-dpo with Docker Model Runner:
```
docker model run hf.co/sathiiiii/polyalign-qwen2.5-3b-en-dpo
```

polyalign

This model is a fine-tuned version of sathiiiii/polyalign-qwen2.5-3b-en-sft on the polyalign_dpo_train dataset. It achieves the following results on the evaluation set:

Loss: 0.3380
Rewards/chosen: -1.0773
Rewards/rejected: -4.7114
Rewards/accuracies: 0.8866
Rewards/margins: 3.6341
Logps/chosen: -102.4047
Logps/rejected: -83.3126
Logits/chosen: -2.2493
Logits/rejected: -2.2458

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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/chosen	Logps/rejected	Logits/chosen	Logits/rejected
0.2949	0.4307	3000	0.3603	-1.1292	-4.2747	0.8788	3.1456	-102.9238	-78.9461	-2.2672	-2.2695
0.2779	0.8615	6000	0.3380	-1.0773	-4.7114	0.8866	3.6341	-102.4047	-83.3126	-2.2493	-2.2458

Framework versions

Transformers 4.56.2
Pytorch 2.9.1+rocm6.3
Datasets 4.0.0
Tokenizers 0.22.2

Downloads last month: 5

Safetensors

Model size

242k params

Tensor type

BF16

Model tree for sathiiiii/polyalign-qwen2.5-3b-en-dpo

Base model

Qwen/Qwen2.5-3B

Finetuned

sathiiiii/polyalign-qwen2.5-3b-en-sft

Finetuned

(1)

this model