Instructions to use IEITYuan/Yuan2-2B-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IEITYuan/Yuan2-2B-hf with Transformers:

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

pipe = pipeline("text-generation", model="IEITYuan/Yuan2-2B-hf", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("IEITYuan/Yuan2-2B-hf", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use IEITYuan/Yuan2-2B-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IEITYuan/Yuan2-2B-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IEITYuan/Yuan2-2B-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IEITYuan/Yuan2-2B-hf

SGLang

How to use IEITYuan/Yuan2-2B-hf 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 "IEITYuan/Yuan2-2B-hf" \
    --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": "IEITYuan/Yuan2-2B-hf",
		"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 "IEITYuan/Yuan2-2B-hf" \
        --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": "IEITYuan/Yuan2-2B-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IEITYuan/Yuan2-2B-hf with Docker Model Runner:
```
docker model run hf.co/IEITYuan/Yuan2-2B-hf
```

Yuan2-2B-hf / config_cpu.json

IEIT-Yuan

update cpu

ee5c0f2 over 2 years ago

raw

history blame contribute delete

1.01 kB

	{
	"_from_model_config":true,
	"architectures": [
	"YuanForCausalLM"
	],
	"auto_map":{
	"AutoConfig":"configuration_yuan.YuanConfig",
	"AutoModelForCausalLM":"yuan_hf_model.YuanForCausalLM"
	},
	"tokenizer_class":"YuanTokenizer",
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 8192,
	"max_position_embeddings": 8192,
	"model_type": "yuan",
	"num_attention_heads": 32,
	"num_hidden_layers": 24,
	"rms_norm_eps": 1e-06,
	"dropout": 0.1,
	"tie_word_embeddings": true,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.30.0.dev0",
	"use_cache": true,
	"causal_mask": true,
	"use_flash_attention": false,
	"reset_attention_mask": true,
	"reset_position_ids": true,
	"use_loss_mask": false,
	"eod_token": 77185,
	"sep_token": 77187,
	"eod_token_id": 77185,
	"sep_token_id": 77185,
	"pad_token_id": 77185,
	"bos_token_id": 77185,
	"eos_token_id": 77185,
	"mask_token_id": 77185,
	"vocab_size": 135040
	}