Instructions to use baidu/ERNIE-4.5-21B-A3B-Base-PT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use baidu/ERNIE-4.5-21B-A3B-Base-PT with Transformers:

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

pipe = pipeline("text-generation", model="baidu/ERNIE-4.5-21B-A3B-Base-PT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("baidu/ERNIE-4.5-21B-A3B-Base-PT")
model = AutoModelForCausalLM.from_pretrained("baidu/ERNIE-4.5-21B-A3B-Base-PT", 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 baidu/ERNIE-4.5-21B-A3B-Base-PT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "baidu/ERNIE-4.5-21B-A3B-Base-PT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "baidu/ERNIE-4.5-21B-A3B-Base-PT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/baidu/ERNIE-4.5-21B-A3B-Base-PT

SGLang

How to use baidu/ERNIE-4.5-21B-A3B-Base-PT 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 "baidu/ERNIE-4.5-21B-A3B-Base-PT" \
    --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": "baidu/ERNIE-4.5-21B-A3B-Base-PT",
		"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 "baidu/ERNIE-4.5-21B-A3B-Base-PT" \
        --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": "baidu/ERNIE-4.5-21B-A3B-Base-PT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use baidu/ERNIE-4.5-21B-A3B-Base-PT with Docker Model Runner:
```
docker model run hf.co/baidu/ERNIE-4.5-21B-A3B-Base-PT
```

jerrimu commited on Jan 16

Commit

fe87080

verified ·

1 Parent(s): c680438

Delete config.json

Browse files

Files changed (1) hide show

config.json +0 -36

config.json DELETED Viewed

@@ -1,36 +0,0 @@
-{
-  "architectures": [
-    "Ernie4_5_MoeForCausalLM"
-  ],
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 2560,
-  "initializer_range": 0.02,
-  "intermediate_size": 12288,
-  "max_position_embeddings": 131072,
-  "model_type": "ernie4_5_moe",
-  "moe_intermediate_size": 1536,
-  "moe_k": 6,
-  "moe_layer_end_index": 27,
-  "moe_layer_interval": 1,
-  "moe_layer_start_index": 1,
-  "moe_norm_min": 1e-12,
-  "moe_num_experts": 64,
-  "moe_num_shared_experts": 2,
-  "num_attention_heads": 20,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 4,
-  "output_router_logits": false,
-  "pad_token_id": 0,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 500000.0,
-  "router_aux_loss_coef": 0.001,
-  "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.54.0.dev0",
-  "use_bias": false,
-  "use_cache": true,
-  "vocab_size": 103424
-}