Instructions to use PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw with Transformers:

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

pipe = pipeline("text-generation", model="PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw")
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("PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw")
model = AutoModelForCausalLM.from_pretrained("PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw", 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 PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw

SGLang

How to use PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw 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 "PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw" \
    --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": "PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw",
		"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 "PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw" \
        --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": "PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw with Docker Model Runner:
```
docker model run hf.co/PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Phi-3 MoE mini 4k instruct raw

The is a 8x MoE version of microsoft/Phi-3-mini-4k-instruct. It is based on the Llamafied version vonjack/Phi-3-mini-4k-instruct-LLaMAfied of Gan Feng.

It was created with the help of mergekit.

As the router was initialized randomly during merging, this is a raw model. It should be trained before it can be used.

Licensing

Licensed under the MIT License (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License by reviewing the file LICENSE in the repository.

Downloads last month: 25

Safetensors

Model size

21B params

Tensor type

BF16

Model tree for PhilipMay/Phi-3-mini-4k-instruct-LLaMAfied-8xMoE-raw

Quantizations

1 model