Instructions to use yangzhao02/qwen2.5-7b-hinge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yangzhao02/qwen2.5-7b-hinge with Transformers:

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

pipe = pipeline("text-generation", model="yangzhao02/qwen2.5-7b-hinge")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yangzhao02/qwen2.5-7b-hinge")
model = AutoModelForCausalLM.from_pretrained("yangzhao02/qwen2.5-7b-hinge")
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

vLLM

How to use yangzhao02/qwen2.5-7b-hinge with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yangzhao02/qwen2.5-7b-hinge"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yangzhao02/qwen2.5-7b-hinge",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yangzhao02/qwen2.5-7b-hinge

SGLang

How to use yangzhao02/qwen2.5-7b-hinge 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 "yangzhao02/qwen2.5-7b-hinge" \
    --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": "yangzhao02/qwen2.5-7b-hinge",
		"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 "yangzhao02/qwen2.5-7b-hinge" \
        --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": "yangzhao02/qwen2.5-7b-hinge",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yangzhao02/qwen2.5-7b-hinge with Docker Model Runner:
```
docker model run hf.co/yangzhao02/qwen2.5-7b-hinge
```

qwen2.5-7b-hinge

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct-1M on the yangzhao02/ListUltraFeedback dataset. It achieves the following results on the evaluation set:

Loss: 0.4210
Logps: -669.7120
Logits: -0.5740
Rank Correct Batch: 16.1545
Rank Pair Batch: 28.0
Rank Accuracy Batch: 0.5769

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: 16
total_train_batch_size: 128
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Logps	Logits	Rank Correct Batch	Rank Pair Batch	Rank Accuracy Batch
0.4556	0.2672	125	0.4577	-591.6161	-0.5776	15.6707	28.0	0.5597
0.431	0.5344	250	0.4297	-651.6651	-0.5554	16.0528	28.0	0.5733
0.4226	0.8016	375	0.4214	-671.2625	-0.5722	16.1870	28.0	0.5781

Framework versions

Transformers 4.45.1
Pytorch 2.6.0+cu126
Datasets 2.19.1
Tokenizers 0.20.3

Downloads last month: 2

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for yangzhao02/qwen2.5-7b-hinge

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct-1M

Finetuned

(51)

this model