Instructions to use Fizzarolli/phi3-4x4b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fizzarolli/phi3-4x4b-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Fizzarolli/phi3-4x4b-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Fizzarolli/phi3-4x4b-v1")
model = AutoModelForCausalLM.from_pretrained("Fizzarolli/phi3-4x4b-v1", 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 Fizzarolli/phi3-4x4b-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Fizzarolli/phi3-4x4b-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": "Fizzarolli/phi3-4x4b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Fizzarolli/phi3-4x4b-v1

SGLang

How to use Fizzarolli/phi3-4x4b-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 "Fizzarolli/phi3-4x4b-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": "Fizzarolli/phi3-4x4b-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 "Fizzarolli/phi3-4x4b-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": "Fizzarolli/phi3-4x4b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Fizzarolli/phi3-4x4b-v1 with Docker Model Runner:
```
docker model run hf.co/Fizzarolli/phi3-4x4b-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

phi 3 4x4b

a continually pretrained phi3-mini sparse moe upcycle

benchmarks

ran locally

	Microsoft/phi-3-4k-instruct	Fizzarolli/phi3-4x4b-v1
MMLU acc. (0-shot)	0.6799	0.6781
Hellaswag acc. (0-shot)	0.6053	0.5962
ARC-E acc. (0-shot)	0.8325	0.8367
ARC-C acc. (0-shot)	0.5546	0.5606

honestly i was expecting it to do worse :p, but those are all within a margin of error! so it didn't lose any performance, at least

open llm leaderboard

todo!

support me on ko-fi!

~~please i need money to stay alive and keep making models~~

notes

not trained on instruct data. it's pretty likely that it won't be much different from phi 3 if you use it like that, if not worse due to any forgetting of instruct formats during the continued training.

future experiments

the datasets for this were literally chosen on a whim. perhaps experiment with a further filtered HuggingFaceFW/fineweb-edu?
actually freeze the gate layers next time (see Chen et. al, 2023), oops
MOAR TRAINING, this only went up to ~0.2 of an epoch because i ran out of dolar

Downloads last month: 13

Safetensors

Model size

11B params

Tensor type

BF16

Model tree for Fizzarolli/phi3-4x4b-v1

Quantizations

2 models

Datasets used to train Fizzarolli/phi3-4x4b-v1

Paper for Fizzarolli/phi3-4x4b-v1

Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers

Paper • 2303.01610 • Published Mar 2, 2023