Instructions to use YeonwooSung/Neos-Phi-3-14B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YeonwooSung/Neos-Phi-3-14B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="YeonwooSung/Neos-Phi-3-14B-v0.1", 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("YeonwooSung/Neos-Phi-3-14B-v0.1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("YeonwooSung/Neos-Phi-3-14B-v0.1", trust_remote_code=True, 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YeonwooSung/Neos-Phi-3-14B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YeonwooSung/Neos-Phi-3-14B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YeonwooSung/Neos-Phi-3-14B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YeonwooSung/Neos-Phi-3-14B-v0.1

SGLang

How to use YeonwooSung/Neos-Phi-3-14B-v0.1 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 "YeonwooSung/Neos-Phi-3-14B-v0.1" \
    --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": "YeonwooSung/Neos-Phi-3-14B-v0.1",
		"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 "YeonwooSung/Neos-Phi-3-14B-v0.1" \
        --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": "YeonwooSung/Neos-Phi-3-14B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use YeonwooSung/Neos-Phi-3-14B-v0.1 with Docker Model Runner:
```
docker model run hf.co/YeonwooSung/Neos-Phi-3-14B-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

Model Card for Model ID

microsoft/Phi-3-medium-4k-instruct trained with ORPO trainer.

Training Details

Training Data

mlabonne/orpo-dpo-mix-40k is used for finetuning this model.

[More Information Needed]

Training Procedure

Trained with ORPO trainer, and only first 5K rows are used for finetuning (5K out of 40K).

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	26.84
IFEval (0-Shot)	40.22
BBH (3-Shot)	46.63
MATH Lvl 5 (4-Shot)	16.69
GPQA (0-shot)	7.38
MuSR (0-shot)	10.53
MMLU-PRO (5-shot)	39.60

Downloads last month: 38

Safetensors

Model size

14B params

Tensor type

BF16

Model tree for YeonwooSung/Neos-Phi-3-14B-v0.1

Base model

microsoft/Phi-3-medium-4k-instruct

Finetuned

(104)

this model

Quantizations

2 models

Dataset used to train YeonwooSung/Neos-Phi-3-14B-v0.1

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

40.220
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

46.630
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

16.690
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

7.380
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

10.530
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

39.600