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

Libraries

How to use QuantFactory/YuLan-Mini-GGUF with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/YuLan-Mini-GGUF", dtype="auto")

llama-cpp-python

How to use QuantFactory/YuLan-Mini-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/YuLan-Mini-GGUF",
	filename="YuLan-Mini.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/YuLan-Mini-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/YuLan-Mini-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/YuLan-Mini-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/YuLan-Mini-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/YuLan-Mini-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf QuantFactory/YuLan-Mini-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/YuLan-Mini-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf QuantFactory/YuLan-Mini-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/YuLan-Mini-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/YuLan-Mini-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/YuLan-Mini-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/QuantFactory/YuLan-Mini-GGUF:Q4_K_M

SGLang

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

Ollama
How to use QuantFactory/YuLan-Mini-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/YuLan-Mini-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/YuLan-Mini-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/YuLan-Mini-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/YuLan-Mini-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/YuLan-Mini-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/YuLan-Mini-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/YuLan-Mini-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/YuLan-Mini-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/YuLan-Mini-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.YuLan-Mini-GGUF-Q4_K_M

List all available models

lemonade list

YuLan-Mini-GGUF / README.md

aashish1904

Upload README.md with huggingface_hub

b3cfc3f verified over 1 year ago

preview code

raw

history blame contribute delete

12.6 kB

metadata

license: mit
library_name: transformers
pipeline_tag: text-generation
datasets:
  - yulan-team/YuLan-Mini-Datasets
  - HuggingFaceFW/fineweb-edu
  - bigcode/the-stack-v2
  - mlfoundations/dclm-baseline-1.0
  - math-ai/AutoMathText
  - gair-prox/open-web-math-pro
  - RUC-AIBOX/long_form_thought_data_5k
  - internlm/Lean-Workbook
  - internlm/Lean-Github
  - deepseek-ai/DeepSeek-Prover-V1
  - ScalableMath/Lean-STaR-base
  - ScalableMath/Lean-STaR-plus
  - ScalableMath/Lean-CoT-base
  - ScalableMath/Lean-CoT-plus
  - opencsg/chinese-fineweb-edu
  - liwu/MNBVC
  - vikp/textbook_quality_programming
  - HuggingFaceTB/smollm-corpus
  - OpenCoder-LLM/opc-annealing-corpus
  - OpenCoder-LLM/opc-sft-stage1
  - OpenCoder-LLM/opc-sft-stage2
  - XinyaoHu/AMPS_mathematica
  - deepmind/math_dataset
  - mrfakename/basic-math-10m
  - microsoft/orca-math-word-problems-200k
  - AI-MO/NuminaMath-CoT
  - HuggingFaceTB/cosmopedia
  - MU-NLPC/Calc-ape210k
  - manu/project_gutenberg
  - storytracer/LoC-PD-Books
  - allenai/dolma
language:
  - en
  - zh
tags:
  - code
  - math
arxiv: 2412.17743
model-index:
  - name: YuLan-Mini
    results:
      - task:
          type: text-generation
        dataset:
          type: openai_humaneval
          name: HumanEval
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.64
            verified: false
      - task:
          type: text-generation
        dataset:
          type: mbpp
          name: MBPP
        metrics:
          - name: pass@1
            type: pass@1
            value: 0.659
            verified: false
      - task:
          type: text-generation
        dataset:
          type: math-500
          name: MATH-500
        metrics:
          - name: maj@1
            type: maj@1
            value: 0.378
            verified: false
      - task:
          type: text-generation
        dataset:
          type: gsm8k
          name: GSM8K
        metrics:
          - name: maj@1
            type: maj@1
            value: 0.684
            verified: false

QuantFactory/YuLan-Mini-GGUF

This is quantized version of yulan-team/YuLan-Mini created using llama.cpp

Original Model Card

Important Notice: This is a pre-trained base model without instruction-following capabilities. The SFT version will be released within a few weeks.

YuLan-Mini: An Open Data-efficient Language Model

YuLan-Mini is a lightweight language model with 2.4 billion parameters. It achieves performance comparable to industry-leading models trained on significantly more data, despite being pre-trained on only 1.08T tokens. The model excels particularly in the domains of mathematics and code. To facilitate reproducibility, we will open-source the relevant pre-training resources.

Model Downloads 🔗

Model weights will be uploaded after final preparations.

Model	Context Length	SFT
YuLan-Mini (Recommended)	28K	❎
YuLan-Mini-2.4B-4K	4K	❎
YuLan-Mini-Instruct	Comming soon	✅

Features 🌟

Our pre-training methodology improves training efficiency through three key innovations:

an elaborately designed data pipeline that combines data cleaning with data schedule strategies;
a systematic optimization method that can effectively mitigate training instability;
an effective annealing approach that integrate targeted data selection and long context training.

Behchmarks 🌟

Models	Model Size	# Train Tokens	Context Length	MATH 500	GSM 8K	Human Eval	MBPP	RACE Middle	RACE High	RULER
MiniCPM	2.6B	1.06T	4K	15.00	53.83	50.00*	47.31	56.61	44.27	N/A
Qwen-2	1.5B	7T	128K	22.60	46.90*	34.80*	46.90*	55.77	43.69	60.16
Qwen2.5	0.5B	18T	128K	23.60	41.60*	30.50*	39.30*	52.36	40.31	49.23
Qwen2.5	1.5B	18T	128K	45.40	68.50*	37.20*	60.20*	58.77	44.33	68.26
Gemma2	2.6B	2T	8K	18.30*	30.30*	19.50*	42.10*	-	-	N/A
StableLM2	1.7B	2T	4K	-	20.62	8.50*	17.50	56.33	45.06	N/A
SmolLM2	1.7B	11T	8K	11.80	-	23.35	45.00	55.77	43.06	N/A
Llama3.2	3.2B	9T	128K	7.40	-	29.30	49.70	55.29	43.34	77.06
YuLan-Mini	2.4B	1.04T	4K	32.60	66.65	61.60	66.70	55.71	43.58	N/A
YuLan-Mini	2.4B	1.08T	28K	37.80	68.46	64.00	65.90	57.18	44.57	51.48

Models	LAMBADA	MMLU	CMMLU	CEval	HellaSwag	WinoGrande	StoryCloze	ARC-e	ARC-c
MiniCPM-2.6B	61.91	53.37	48.97	48.24	67.92	65.74	78.51	55.51	43.86
Qwen2-1.5B	64.68	55.90	70.76	71.94	66.11	66.14	77.60	62.21	42.92
Qwen2.5-0.5B	52.00	47.50	52.17	54.27	50.54	55.88	71.67	56.10	39.51
Qwen2.5-1.5B	62.12	60.71	67.82	69.05	67.18	64.48	76.80	71.51	53.41
Gemma2-2.6B	-	52.20*	-	28.00*	74.60*	71.50*	-	-	55.70*
StableLM2-1.7B	66.15	40.37	29.29	26.99	69.79	64.64	78.56	54.00	40.78
SmolLM2-1.7B	67.42	51.91	33.46	35.10	72.96	67.40	79.32	44.82	35.49
Llama3.2-3B	69.08	63.40	44.44	44.49	75.62	67.48	76.80	70.12	48.81
YuLan-Mini	64.72	51.79	48.35	51.47	68.65	67.09	76.37	69.87	50.51
YuLan-Mini	65.67	49.10	45.45	48.23	67.22	67.24	75.89	67.47	49.32

Pre-Training Resources 🔧

To enhance research transparency and reproducibility, we are open-sourcing relevant pre-training resources:

1. Pre-training and Evaluation Code

The pre-training and evaluation code will be released in a future update.

2. Intermediate Stage Checkpoints

The intermediate stage checkpoints are released in YuLan-Mini.

3. Optimizer States Before Annealing

YuLan-Mini-Before-Annealing

4. The Used Open-Source Datasets

Used-Datasets-List

5. Data Distribution for every phase

6. Synthetic Data

Data cleaning and synthesis pipeline:

The synthetic data we are using is released in YuLan-Mini-Datasets

7. Intermediate Optimizer States

Intermediate optimizer states will be released in a future update.

What you can do with these pre-training resources

Pre-train your own LLM. You can use our data and curriculum to train a model that's just as powerful as YuLan-Mini.
Perform your own learning rate annealing. During the annealing phase, YuLan-Mini's learning ability is at its peak. You can resume training from the checkpoint before annealing and use your own dataset for learning rate annealing.
Fine-tune the Instruct version of the LLM. You can use the YuLan-Mini base model to train your own Instruct version.
Training dynamics research. You can use YuLan-Mini's intermediate checkpoints to explore internal changes during the pre-training process.
Synthesize your own data. You can use YuLan-Mini's data pipeline to clean and generate your own dataset.

Quick Start 💻

Below is a simple example for inference using Huggingface:

Huggingface Inference Example

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("yulan-team/YuLan-Mini")
model = AutoModelForCausalLM.from_pretrained("yulan-team/YuLan-Mini", torch_dtype=torch.bfloat16)

# Input text
input_text = "Renmin University of China is"
inputs = tokenizer(input_text, return_tensors="pt")

# Completion
output = model.generate(inputs["input_ids"], max_new_tokens=100)
print(tokenizer.decode(output[0], skip_special_tokens=True))

vLLM Serve Example

vllm serve yulan-team/YuLan-Mini --dtype bfloat16

SGLang Serve Example

python -m sglang.launch_server --model-path yulan-team/YuLan-Mini --port 30000 --host 0.0.0.0

The Team

YuLan-Mini is developed and maintained by AI Box, Renmin University of China.

License

The code in this repository is released under the MIT License.
Policies regarding the use of model weights, intermediate optimizer states, and training data will be announced in future updates.
Limitations: Despite our efforts to mitigate safety concerns and encourage the generation of ethical and lawful text, the probabilistic nature of language models may still lead to unexpected outputs. For instance, responses might contain bias, discrimination, or other harmful content. Please refrain from disseminating such content. We are not liable for any consequences arising from the spread of harmful information.

Citation

If you find YuLan-Mini helpful for your research or development, please cite our technical report:

@misc{hu2024yulanmini,
      title={YuLan-Mini: An Open Data-efficient Language Model}, 
      author={Yiwen Hu and Huatong Song and Jia Deng and Jiapeng Wang and Jie Chen and Kun Zhou and Yutao Zhu and Jinhao Jiang and Zican Dong and Wayne Xin Zhao and Ji-Rong Wen},
      year={2024},
      eprint={2412.17743},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.17743}, 
}