Instructions to use M4-ai/Hercules-phi-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use M4-ai/Hercules-phi-2 with Transformers:

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

pipe = pipeline("text-generation", model="M4-ai/Hercules-phi-2", trust_remote_code=True)

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

tokenizer = AutoTokenizer.from_pretrained("M4-ai/Hercules-phi-2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("M4-ai/Hercules-phi-2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use M4-ai/Hercules-phi-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "M4-ai/Hercules-phi-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "M4-ai/Hercules-phi-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/M4-ai/Hercules-phi-2

SGLang

How to use M4-ai/Hercules-phi-2 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 "M4-ai/Hercules-phi-2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "M4-ai/Hercules-phi-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "M4-ai/Hercules-phi-2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "M4-ai/Hercules-phi-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use M4-ai/Hercules-phi-2 with Docker Model Runner:
```
docker model run hf.co/M4-ai/Hercules-phi-2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Hercules-phi-2

We fine-tuned phi2 on Locutusque's Hercules-v4.5.

Model Details

Model Description

This model has capabilities in math, coding, function calling, roleplay, and more. We fine-tuned it using all examples of Hercules-v4.5.

Developed by: M4-ai
Language(s) (NLP): English
License: apache-2.0

Uses

General purpose assistant, question answering, chain-of-thought, etc..

Evaluation

Coming soon

Training Details

Training Data

https://huggingface.co/datasets/Locutusque/hercules-v4.5

Training Hyperparameters

Training regime: bf16 non-mixed precision

Technical Specifications

Hardware

We used 8 Kaggle TPUs, and we trained at a global batch size of 1152.

Downloads last month: 24

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for M4-ai/Hercules-phi-2

Quantizations

1 model

M4-ai
/

Hercules-phi-2