Instructions to use macadeliccc/SOLAR-polyglot-4x10.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use macadeliccc/SOLAR-polyglot-4x10.7b with Transformers:

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

pipe = pipeline("text-generation", model="macadeliccc/SOLAR-polyglot-4x10.7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("macadeliccc/SOLAR-polyglot-4x10.7b")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/SOLAR-polyglot-4x10.7b")
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

vLLM

How to use macadeliccc/SOLAR-polyglot-4x10.7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "macadeliccc/SOLAR-polyglot-4x10.7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "macadeliccc/SOLAR-polyglot-4x10.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/macadeliccc/SOLAR-polyglot-4x10.7b

SGLang

How to use macadeliccc/SOLAR-polyglot-4x10.7b 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 "macadeliccc/SOLAR-polyglot-4x10.7b" \
    --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": "macadeliccc/SOLAR-polyglot-4x10.7b",
		"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 "macadeliccc/SOLAR-polyglot-4x10.7b" \
        --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": "macadeliccc/SOLAR-polyglot-4x10.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use macadeliccc/SOLAR-polyglot-4x10.7b with Docker Model Runner:
```
docker model run hf.co/macadeliccc/SOLAR-polyglot-4x10.7b
```

🌞🚀 SOLAR-polyglot-4x10.7

Multilingual experiment based on my mixtral collection Polyglot

The model is proficient in:

English
German
Korean

🌅 Code Example

Example with evaluation script also available in colab

from transformers import AutoModelForCausalLM, AutoTokenizer

def generate_response(prompt):
    """
    Generate a response from the model based on the input prompt.
    Args:
    prompt (str): Prompt for the model.
    Returns:
    str: The generated response from the model.
    """

    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=512, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.pad_token_id)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)

    return response

model_id = "macadeliccc/SOLAR-polyglot-4x10.7b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True)

prompt = "Explain the proof of Fermat's Last Theorem and its implications in number theory."

print("Response:")
print(generate_response(prompt), "\n")

Evaluations

TODO

📚 Citations

@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: 8

Safetensors

Model size

36B params

Tensor type

BF16

Collections including macadeliccc/SOLAR-polyglot-4x10.7b

SOLAR-MoE

Collection

SOLAR-10.7b MoE configurations • 5 items • Updated Mar 2 • 1

Polyglot

Collection

MoE models that are fluent in multiple languages. This collection is English, Chinese and Japanese • 4 items • Updated Mar 2

Paper for macadeliccc/SOLAR-polyglot-4x10.7b

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

Paper • 2312.15166 • Published Dec 23, 2023 • 61