Instructions to use yulan-team/YuLan-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yulan-team/YuLan-Mini with Transformers:

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

pipe = pipeline("text-generation", model="yulan-team/YuLan-Mini")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yulan-team/YuLan-Mini")
model = AutoModelForCausalLM.from_pretrained("yulan-team/YuLan-Mini", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yulan-team/YuLan-Mini with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yulan-team/YuLan-Mini

SGLang

How to use yulan-team/YuLan-Mini 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 "yulan-team/YuLan-Mini" \
    --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": "yulan-team/YuLan-Mini",
		"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 "yulan-team/YuLan-Mini" \
        --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": "yulan-team/YuLan-Mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yulan-team/YuLan-Mini with Docker Model Runner:
```
docker model run hf.co/yulan-team/YuLan-Mini
```

IvanHU commited on Dec 26, 2024

Commit

babaf3f

verified ·

1 Parent(s): 568e186

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -4

README.md CHANGED Viewed

@@ -144,11 +144,9 @@ Optimizer states before annealing will be released in a future update.
 <details><summary>5. Data Distribution for every phase</summary>
-<a href="https://github.com/RUC-GSAI/YuLan-Mini/blob/main/pretrain/final.pdf">High-resolution version</a>
 <a href="https://github.com/RUC-GSAI/YuLan-Mini/blob/main/pretrain/final.pdf">
   <div align=center>
-    <img src="https://github.com/RUC-GSAI/YuLan-Mini/blob/main/assets/data_distribution_for_every_phase.png">
   </div>
 </a>
@@ -159,7 +157,7 @@ Optimizer states before annealing will be released in a future update.
 Data cleaning and synthesis pipeline:
 <div align=center>
-<img src="https://github.com/RUC-GSAI/YuLan-Mini/blob/main/assets/data-pipeline.png">
 </div>
 The synthetic data we are using is released in <a href="https://huggingface.co/collections/yulan-team/yulan-mini-676d214b24376739b00d95f3">YuLan-Mini-Datasets</a>

 <details><summary>5. Data Distribution for every phase</summary>
 <a href="https://github.com/RUC-GSAI/YuLan-Mini/blob/main/pretrain/final.pdf">
   <div align=center>
+    <img src="assets/data_distribution_for_every_phase.png">
   </div>
 </a>
 Data cleaning and synthesis pipeline:
 <div align=center>
+<img src="assets/data-pipeline.png">
 </div>
 The synthetic data we are using is released in <a href="https://huggingface.co/collections/yulan-team/yulan-mini-676d214b24376739b00d95f3">YuLan-Mini-Datasets</a>