Instructions to use HighCWu/Embformer-MiniMind-0.1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HighCWu/Embformer-MiniMind-0.1B with Transformers:

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

pipe = pipeline("text-generation", model="HighCWu/Embformer-MiniMind-0.1B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("HighCWu/Embformer-MiniMind-0.1B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HighCWu/Embformer-MiniMind-0.1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HighCWu/Embformer-MiniMind-0.1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HighCWu/Embformer-MiniMind-0.1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HighCWu/Embformer-MiniMind-0.1B

SGLang

How to use HighCWu/Embformer-MiniMind-0.1B 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 "HighCWu/Embformer-MiniMind-0.1B" \
    --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": "HighCWu/Embformer-MiniMind-0.1B",
		"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 "HighCWu/Embformer-MiniMind-0.1B" \
        --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": "HighCWu/Embformer-MiniMind-0.1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HighCWu/Embformer-MiniMind-0.1B with Docker Model Runner:
```
docker model run hf.co/HighCWu/Embformer-MiniMind-0.1B
```

Embformer-MiniMind-0.1B

A 0.1B sft model of the reasearch note Embformer: An Embedding-Weight-Only Transformer Architecture, which trained on jingyaogong/minimind_dataset.

Run commands in the terminal:

pip install "transformers @ git+https://github.com/huggingface/transformers.git@cb0f604"

The following contains a code snippet illustrating how to use the model generate content based on given inputs.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "HighCWu/Embformer-MiniMind-0.1B"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(
    model_name,
    trust_remote_code=True,
    cache_dir=".cache"
)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
    cache_dir=".cache"
)

# prepare the model input
prompt = "请为我讲解“大语言模型”这个概念。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    input_ids=model_inputs['input_ids'],
    attention_mask=model_inputs['attention_mask'],
    max_new_tokens=8192
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

print(tokenizer.decode(output_ids, skip_special_tokens=True))