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

Libraries

How to use HBboy/test with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HBboy/test")
model = AutoModelForCausalLM.from_pretrained("HBboy/test")
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 HBboy/test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/HBboy/test

SGLang

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

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

HBboy commited on Jan 23, 2025

Commit

3ebfa38

verified ·

1 Parent(s): 6c300c2

Upload training_args.yaml with huggingface_hub

Browse files

Files changed (1) hide show

training_args.yaml +29 -0

training_args.yaml ADDED Viewed

	@@ -0,0 +1,29 @@

+bf16: true
+cutoff_len: 2048
+dataset: xiaosui-train,identity
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: full
+flash_attn: auto
+gradient_accumulation_steps: 8
+learning_rate: 5.0e-05
+logging_steps: 5
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 5000
+model_name_or_path: Qwen/Qwen2.5-0.5B-Instruct
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Qwen2.5-0.5B-Instruct/full/train_2025-01-23-16-59-22
+packing: false
+per_device_train_batch_size: 2
+plot_loss: true
+preprocessing_num_workers: 16
+report_to:
+- wandb
+save_steps: 100
+stage: sft
+template: qwen
+trust_remote_code: true
+warmup_steps: 4