Instructions to use li-ovo/NER_Game with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use li-ovo/NER_Game with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("li-ovo/NER_Game")
model = AutoModelForCausalLM.from_pretrained("li-ovo/NER_Game", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use li-ovo/NER_Game with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/li-ovo/NER_Game

SGLang

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

Docker Model Runner
How to use li-ovo/NER_Game with Docker Model Runner:
```
docker model run hf.co/li-ovo/NER_Game
```

NER_Game / serving_config.json

li-ovo

Update NER_Game to R27 merged multi-game BF16 release

5c86bf0 verified 4 days ago

Raw History Blame Contribute Delete

478 Bytes

	{
	"model_type": "merged",
	"served_model_name": "r27-release",
	"target_gpu": "A10",
	"dtype": "bfloat16",
	"tensor_parallel_size": 1,
	"gpu_memory_utilization": 0.85,
	"max_model_len": 4096,
	"max_num_seqs": 4,
	"enable_lora": false,
	"thinking_enabled": false,
	"chat_template_kwargs": {
	"enable_thinking": false
	},
	"temperature": 0,
	"max_tokens": 2048,
	"output_channel": "content",
	"reasoning_parser": null,
	"a10_hardware_validation": "not_run"
	}