Instructions to use DarqueDante/Phi3Mix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DarqueDante/Phi3Mix with Transformers:

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

pipe = pipeline("text-generation", model="DarqueDante/Phi3Mix", 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("DarqueDante/Phi3Mix", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("DarqueDante/Phi3Mix", 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 Settings

vLLM

How to use DarqueDante/Phi3Mix with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DarqueDante/Phi3Mix"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DarqueDante/Phi3Mix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DarqueDante/Phi3Mix

SGLang

How to use DarqueDante/Phi3Mix 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 "DarqueDante/Phi3Mix" \
    --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": "DarqueDante/Phi3Mix",
		"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 "DarqueDante/Phi3Mix" \
        --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": "DarqueDante/Phi3Mix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DarqueDante/Phi3Mix with Docker Model Runner:
```
docker model run hf.co/DarqueDante/Phi3Mix
```

Phi3Mix

Phi3Mix is a Mixture of Experts (MoE) made with the following models using Phi3_LazyMergekit:

🧩 Configuration

base_model: microsoft/Phi-3-medium-128k-instruct
gate_mode: cheap_embed
experts_per_token: 1
dtype: float16
experts:
  - source_model: microsoft/Phi-3-medium-128k-instruct
    positive_prompts: ["research, logic, math, science"]
  - source_model: microsoft/Phi-3-medium-128k-instruct
    positive_prompts: ["creative, art"]

💻 Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = "DarqueDante/Phi3Mix"

tokenizer = AutoTokenizer.from_pretrained(model)

model = AutoModelForCausalLM.from_pretrained(
    model,
    trust_remote_code=True,
)

prompt="How many continents are there?"
input = f"<|system|>You are a helpful AI assistant.<|end|><|user|>{prompt}<|assistant|>"
tokenized_input = tokenizer.encode(input, return_tensors="pt")

outputs = model.generate(tokenized_input, max_new_tokens=128, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(tokenizer.decode(outputs[0]))

Downloads last month: 4

Safetensors

Model size

25B params

Tensor type

F16

Model tree for DarqueDante/Phi3Mix

Base model

microsoft/Phi-3-medium-128k-instruct

Finetuned

(7)

this model