Instructions to use pahautelman/phi2-ner-dpo-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pahautelman/phi2-ner-dpo-v1 with Transformers:

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

pipe = pipeline("text-generation", model="pahautelman/phi2-ner-dpo-v1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pahautelman/phi2-ner-dpo-v1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("pahautelman/phi2-ner-dpo-v1", trust_remote_code=True)
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 pahautelman/phi2-ner-dpo-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pahautelman/phi2-ner-dpo-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pahautelman/phi2-ner-dpo-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pahautelman/phi2-ner-dpo-v1

SGLang

How to use pahautelman/phi2-ner-dpo-v1 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 "pahautelman/phi2-ner-dpo-v1" \
    --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": "pahautelman/phi2-ner-dpo-v1",
		"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 "pahautelman/phi2-ner-dpo-v1" \
        --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": "pahautelman/phi2-ner-dpo-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pahautelman/phi2-ner-dpo-v1 with Docker Model Runner:
```
docker model run hf.co/pahautelman/phi2-ner-dpo-v1
```

Phi-2 model fine-tuned for named entity recognition task

The model was fine-tuned using one quarter of the ConLL 2012 OntoNotes v5 dataset.

Dataset Source: conll2012_ontonotesv5
Subset Used: English_v12
Number of Examples: 21,817

The prompts and expected outputs were constructed as described in [1].

Example input:

I am an excelent linquist. The task is to label location entities in the given sentence. Below are some examples

Input: Only France and Britain backed Fischler's proposal.
Output: Only @@France## and @@Britain## backed Fischler's proposal.

Input: Germany imported 47,000 sheeps from Britain last year, nearly half of total imports.
Output: @@Germany## imported 47,000 sheeps from @@Britain## last year, nearly half of total imports.

Input: It brought in 4275 tonnes of British mutton, some 10% of overall imports.
Output: It brought in 4275 tonnes of British mutton, some 10% of overall imports.

Input: China says Taiwan spoils atmosphere for talks.
Output:

Expected output:

@@China## says @@Taiwan## spoils atmosphere for talks.

Model Trained Using AutoTrain

This model was trained using DPO AutoTrain trainer. For more information, please visit AutoTrain.

Hyperparameters:

{
    "model": "microsoft/phi-2",
    "train_split": "train",
    "valid_split": null,
    "add_eos_token": true,
    "block_size": 1024,
    "model_max_length": 2048,
    "padding": "right",
    "trainer": "dpo",
    "use_flash_attention_2": false,
    "log": "tensorboard",
    "disable_gradient_checkpointing": false,
    "logging_steps": -1,
    "evaluation_strategy": "epoch",
    "save_total_limit": 1,
    "save_strategy": "epoch",
    "auto_find_batch_size": false,
    "mixed_precision": "bf16",
    "lr": 3e-05,
    "epochs": 1,
    "batch_size": 2,
    "warmup_ratio": 0.05,
    "gradient_accumulation": 1,
    "optimizer": "adamw_torch",
    "scheduler": "linear",
    "weight_decay": 0.0,
    "max_grad_norm": 1.0,
    "seed": 42,
    "apply_chat_template": false,
    "quantization": "int4",
    "target_modules": "",
    "merge_adapter": false,
    "peft": true,
    "lora_r": 16,
    "lora_alpha": 32,
    "lora_dropout": 0.05,
    "model_ref": null,
    "dpo_beta": 0.1,
}

Usage


from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "pahautelman/phi2-ner-dpo-v1"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path
).eval()

prompt = 'Label the person entities in the given sentence: Russian President Vladimir Putin is due to arrive in Havana a few hours from now to become the first post-Soviet leader to visit Cuba.'

inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors='pt')
outputs = model.generate(
    inputs.to(model.device),
    max_new_tokens=9,
    do_sample=False,
)
output = tokenizer.batch_decode(outputs)[0]

# Model response: "Answer: Russian President, Vladimir Putin"
print(output)

References:

[1] Wang et al., GPT-NER: Named entity recognition via large language models 2023

Downloads last month: 3

Safetensors

Model size

3B params

Tensor type

F32

F16

pahautelman
/

phi2-ner-dpo-v1

Phi-2 model fine-tuned for named entity recognition task

Model Trained Using AutoTrain

Usage

References:

Dataset used to train pahautelman/phi2-ner-dpo-v1