Instructions to use jaeyong2/Dynamic_NER with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jaeyong2/Dynamic_NER with Transformers:

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

pipe = pipeline("text-generation", model="jaeyong2/Dynamic_NER")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jaeyong2/Dynamic_NER")
model = AutoModelForCausalLM.from_pretrained("jaeyong2/Dynamic_NER")
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 jaeyong2/Dynamic_NER with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jaeyong2/Dynamic_NER"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jaeyong2/Dynamic_NER",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jaeyong2/Dynamic_NER

SGLang

How to use jaeyong2/Dynamic_NER 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 "jaeyong2/Dynamic_NER" \
    --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": "jaeyong2/Dynamic_NER",
		"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 "jaeyong2/Dynamic_NER" \
        --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": "jaeyong2/Dynamic_NER",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jaeyong2/Dynamic_NER with Docker Model Runner:
```
docker model run hf.co/jaeyong2/Dynamic_NER
```

jaeyong2 commited on Oct 25, 2025

Commit

bf14982

verified ·

1 Parent(s): 78fb3c3

Update README.md

Browse files

Files changed (1) hide show

README.md +48 -0

README.md CHANGED Viewed

@@ -9,3 +9,51 @@ base_model:
 - Qwen/Qwen3-0.6B
 ---

 - Qwen/Qwen3-0.6B
 ---
+### example(En)
+```
+system = """
+You are an AI that dynamically performs Named Entity Recognition (NER).
+You receive a sentence and a list of entity types the user wants to extract, and then identify all entities of those types within the sentence.
+If you cannot find any suitable entities within the sentence, return an empty list.
+"""
+text = """
+Once upon a time, a little boy named Tim went to the park with his mom. They saw a big fountain with water going up and down. Tim was very happy to see it.
+Tim asked his mom, "Can I go near the fountain?" His mom answered, "Yes, but hold my hand tight." Tim held his mom's hand very tight and they walked closer to the fountain. They saw fish in the water and Tim laughed.
+A little girl named Sue came to the fountain too. She asked Tim, "Do you like the fish?" Tim said, "Yes, I like them a lot!" Sue and Tim became friends and played near the fountain until it was time to go home.
+""".strip()
+named_entity = """
+[{'type': 'PERSON', 'description': 'Names of individuals'}, {'type': 'LOCATION', 'description': 'Specific places or structures'}, {'type': 'ANIMAL', 'description': 'Names or types of animals'}]
+""".strip()
+user = f"<sentence>\n{text}\n</sentence>\n\n<entity_list>\n{named_entity}\n</entity_list>\n\n"
+chat = [{"role":"system", "content":system}, {"role":"user", "content":user}]
+chat_text = tokenizer.apply_chat_template(
+            chat,
+            enable_thinking=False,
+            add_generation_prompt=True,
+            tokenize=False
+        )
+model_inputs = tokenizer([chat_text], return_tensors="pt").to(model.device)
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+```
+### result (en)
+```
+<entities>
+[{'text': 'Tim', 'type': 'PERSON'}, {'text': 'mom', 'type': 'PERSON'}, {'text': 'Sue', 'type': 'PERSON'}, {'text': 'park', 'type': 'LOCATION'}, {'text': 'fountain', 'type': 'LOCATION'}, {'text': 'fish', 'type': 'ANIMAL'}]
+</entities>
+```