Instructions to use shadowml/phixtral-4x2_8odd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shadowml/phixtral-4x2_8odd with Transformers:

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

pipe = pipeline("text-generation", model="shadowml/phixtral-4x2_8odd", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("shadowml/phixtral-4x2_8odd", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use shadowml/phixtral-4x2_8odd with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shadowml/phixtral-4x2_8odd"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shadowml/phixtral-4x2_8odd",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shadowml/phixtral-4x2_8odd

SGLang

How to use shadowml/phixtral-4x2_8odd 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 "shadowml/phixtral-4x2_8odd" \
    --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": "shadowml/phixtral-4x2_8odd",
		"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 "shadowml/phixtral-4x2_8odd" \
        --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": "shadowml/phixtral-4x2_8odd",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shadowml/phixtral-4x2_8odd with Docker Model Runner:
```
docker model run hf.co/shadowml/phixtral-4x2_8odd
```

phixtral-4x2_8odd / config.json

shadowml

Upload folder using huggingface_hub

4477d85 verified over 2 years ago

raw

history blame contribute delete

816 Bytes

	{
	"_name_or_path": "mlabonne/phixtral-2x2_8",
	"activation_function": "gelu_new",
	"architectures": [
	"PhiForCausalLM"
	],
	"attn_pdrop": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_phi.PhiConfig",
	"AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
	},
	"embd_pdrop": 0.0,
	"flash_attn": false,
	"flash_rotary": false,
	"fused_dense": false,
	"img_processor": null,
	"initializer_range": 0.02,
	"layer_norm_epsilon": 1e-05,
	"model_type": "phi-msft",
	"n_embd": 2560,
	"n_head": 32,
	"n_head_kv": null,
	"n_inner": null,
	"n_layer": 32,
	"n_positions": 2048,
	"num_experts_per_tok": 2,
	"num_local_experts": 2,
	"resid_pdrop": 0.1,
	"rotary_dim": 32,
	"tie_word_embeddings": false,
	"torch_dtype": "float16",
	"transformers_version": "4.35.2",
	"vocab_size": 51200
	}