Instructions to use mohomin123/M-DIE-M-10.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mohomin123/M-DIE-M-10.7B with Transformers:

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

pipe = pipeline("text-generation", model="mohomin123/M-DIE-M-10.7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mohomin123/M-DIE-M-10.7B")
model = AutoModelForCausalLM.from_pretrained("mohomin123/M-DIE-M-10.7B", 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 mohomin123/M-DIE-M-10.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mohomin123/M-DIE-M-10.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mohomin123/M-DIE-M-10.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mohomin123/M-DIE-M-10.7B

SGLang

How to use mohomin123/M-DIE-M-10.7B 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 "mohomin123/M-DIE-M-10.7B" \
    --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": "mohomin123/M-DIE-M-10.7B",
		"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 "mohomin123/M-DIE-M-10.7B" \
        --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": "mohomin123/M-DIE-M-10.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mohomin123/M-DIE-M-10.7B with Docker Model Runner:
```
docker model run hf.co/mohomin123/M-DIE-M-10.7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Data Is Everything.

To try other models(involving commercial-available model), please check out our Demo Page(🔨constructing)

This model is made by Ados based on upstage/SOLAR-10.7B-Instruct-v1.0.

Train Dataset

Dataset used for training is collected primarily from huggingface and utilized using our own translation model.

Language
- KR 73%
- EN 24%
- Others 3%
Type
- single turn QA (alpaca style) 29%
- multi turn QA (vicuna style) 21%
- instructed QA 26%
- summary 12%
- translation 12%

After collecting data, we removed low quality rows. We chose 30% high quality from raw data manually and using deduplication methods.

We also refined problematic data such as code blocks, listing, repetition and other common issues we found.

Prompt template

### System:
You are an AI assistant, please behave and help the user. Your name is OLLM(오름) by Ados(주식회사아도스), OLLM stands for On-premise LLM.

### User: On-premise LLM이 뭔가요?

### Assistant:

For more informations, please contact us.

To try other models(involving commercial-available model), please check out our Demo Page(🔨constructing)

License

upstage/SOLAR-10.7B-Instruct-v1.0: cc-by-nc-4.0
- Since some non-commercial datasets such as Alpaca are used for fine-tuning, we release this model as cc-by-nc-4.0.

@misc{kim2023solar,
      title={SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling}, 
      author={Dahyun Kim and Chanjun Park and Sanghoon Kim and Wonsung Lee and Wonho Song and Yunsu Kim and Hyeonwoo Kim and Yungi Kim and Hyeonju Lee and Jihoo Kim and Changbae Ahn and Seonghoon Yang and Sukyung Lee and Hyunbyung Park and Gyoungjin Gim and Mikyoung Cha and Hwalsuk Lee and Sunghun Kim},
      year={2023},
      eprint={2312.15166},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Downloads last month: 13

Safetensors

Model size

11B params

Tensor type

F16

Model tree for mohomin123/M-DIE-M-10.7B

Quantizations

3 models

Paper for mohomin123/M-DIE-M-10.7B

SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling

Paper • 2312.15166 • Published Dec 23, 2023 • 62