Instructions to use mlabonne/phixtral-4x2_8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlabonne/phixtral-4x2_8 with Transformers:

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

pipe = pipeline("text-generation", model="mlabonne/phixtral-4x2_8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("mlabonne/phixtral-4x2_8", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mlabonne/phixtral-4x2_8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlabonne/phixtral-4x2_8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlabonne/phixtral-4x2_8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlabonne/phixtral-4x2_8

SGLang

How to use mlabonne/phixtral-4x2_8 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 "mlabonne/phixtral-4x2_8" \
    --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": "mlabonne/phixtral-4x2_8",
		"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 "mlabonne/phixtral-4x2_8" \
        --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": "mlabonne/phixtral-4x2_8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mlabonne/phixtral-4x2_8 with Docker Model Runner:
```
docker model run hf.co/mlabonne/phixtral-4x2_8
```

mlabonne commited on Jan 9, 2024

Commit

f369c13

1 Parent(s): 39a76b7

Update config.json

Browse files

Files changed (1) hide show

config.json +7 -23

config.json CHANGED Viewed

@@ -1,50 +1,34 @@
 {
-  "_name_or_path": "cognitivecomputations/dolphin-2_6-phi-2",
   "activation_function": "gelu_new",
   "architectures": [
-    "MixtralForCausalLM"
   ],
-  "attention_dropout": 0.0,
   "attn_pdrop": 0.0,
   "auto_map": {
-    "AutoConfig": "cognitivecomputations/dolphin-2_6-phi-2--configuration_phi.PhiConfig",
-    "AutoModelForCausalLM": "cognitivecomputations/dolphin-2_6-phi-2--modeling_phi.PhiForCausalLM"
   },
-  "bos_token_id": null,
   "embd_pdrop": 0.0,
-  "eos_token_id": null,
   "flash_attn": false,
   "flash_rotary": false,
   "fused_dense": false,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
   "img_processor": null,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
   "layer_norm_epsilon": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "mixtral",
   "n_embd": 2560,
   "n_head": 32,
   "n_head_kv": null,
   "n_inner": null,
   "n_layer": 32,
   "n_positions": 2048,
-  "num_attention_heads": 32,
   "num_experts_per_tok": 2,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
   "num_local_experts": 4,
-  "output_router_logits": false,
   "resid_pdrop": 0.1,
-  "rms_norm_eps": 1e-06,
-  "rope_theta": 10000.0,
   "rotary_dim": 32,
-  "router_aux_loss_coef": 0.001,
-  "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.36.2",
-  "use_cache": false,
   "vocab_size": 51200
-}

 {
+  "_name_or_path": "mlabonne/phixtral-4x2_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": 4,
   "resid_pdrop": 0.1,
   "rotary_dim": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
   "vocab_size": 51200
+}