Instructions to use IgnoraZ/llama3_synthquestions_dpo_100k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IgnoraZ/llama3_synthquestions_dpo_100k with Transformers:

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

pipe = pipeline("text-generation", model="IgnoraZ/llama3_synthquestions_dpo_100k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("IgnoraZ/llama3_synthquestions_dpo_100k")
model = AutoModelForCausalLM.from_pretrained("IgnoraZ/llama3_synthquestions_dpo_100k")
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 IgnoraZ/llama3_synthquestions_dpo_100k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IgnoraZ/llama3_synthquestions_dpo_100k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IgnoraZ/llama3_synthquestions_dpo_100k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IgnoraZ/llama3_synthquestions_dpo_100k

SGLang

How to use IgnoraZ/llama3_synthquestions_dpo_100k 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 "IgnoraZ/llama3_synthquestions_dpo_100k" \
    --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": "IgnoraZ/llama3_synthquestions_dpo_100k",
		"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 "IgnoraZ/llama3_synthquestions_dpo_100k" \
        --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": "IgnoraZ/llama3_synthquestions_dpo_100k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IgnoraZ/llama3_synthquestions_dpo_100k with Docker Model Runner:
```
docker model run hf.co/IgnoraZ/llama3_synthquestions_dpo_100k
```

IgnoraZ commited on Jun 11, 2025

Commit

54173dd

verified ·

1 Parent(s): 55c24be

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -36,6 +36,7 @@ For more details like hyper-parameters, please refer to our paper.
 ## How to Get Started with the Model
 This is a model in HF format, which can be deployed with common inference frameworks like Transformers, vLLM, SGLang and so on.
 We finetuned it with custom chat template instead of the default one from LLaMA. **Please make sure to use the chat template in the `tokenizer_config.json` when inferring.**
 ## Evaluation

 ## How to Get Started with the Model
 This is a model in HF format, which can be deployed with common inference frameworks like Transformers, vLLM, SGLang and so on.
 We finetuned it with custom chat template instead of the default one from LLaMA. **Please make sure to use the chat template in the `tokenizer_config.json` when inferring.**
 ## Evaluation