Instructions to use macadeliccc/SOLAR-10.7x2_19B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use macadeliccc/SOLAR-10.7x2_19B with Transformers:

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

pipe = pipeline("text-generation", model="macadeliccc/SOLAR-10.7x2_19B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("macadeliccc/SOLAR-10.7x2_19B")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/SOLAR-10.7x2_19B")
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 macadeliccc/SOLAR-10.7x2_19B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "macadeliccc/SOLAR-10.7x2_19B"
# 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-10.7x2_19B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/macadeliccc/SOLAR-10.7x2_19B

SGLang

How to use macadeliccc/SOLAR-10.7x2_19B 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-10.7x2_19B" \
    --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-10.7x2_19B",
		"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-10.7x2_19B" \
        --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-10.7x2_19B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use macadeliccc/SOLAR-10.7x2_19B with Docker Model Runner:
```
docker model run hf.co/macadeliccc/SOLAR-10.7x2_19B
```

🌞🚀 SOLAR-10.7x2_19B

Merge of two Solar-10.7B instruct finetunes.

Performs higher than mistralai/mixtral-8x7b-Instruct-v0.1

🌅 Code Example

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("macadeliccc/SOLAR-math-2x10.7b",load_in_4bit=True)
model = AutoModelForCausalLM.from_pretrained(
    "macadeliccc/SOLAR-math-2x10.7b",
    device_map="auto",
    torch_dtype=torch.float16,
)

conversation = [ {'role': 'user', 'content': 'A rectangle has a length that is twice its width and its area is 50 square meters. Find the dimensions of the rectangle.'} ] 

prompt = tokenizer.apply_chat_template(conversation, tokenize=False, add_generation_prompt=True)

inputs = tokenizer(prompt, return_tensors="pt").to(model.device) 
outputs = model.generate(**inputs, use_cache=True, max_length=4096)
output_text = tokenizer.decode(outputs[0]) 
print(output_text)

Evaluations

model is currently experimental and was evaluated in 4-bit

Tasks	Version	Filter	Metric	Value		Stderr
arc_challenge	Yaml	none	acc	0.5691	±	0.0145
		none	acc_norm	0.5998	±	0.0143
arc_easy	Yaml	none	acc	0.8354	±	0.0076
		none	acc_norm	0.8258	±	0.0078
boolq	Yaml	none	acc	0.8716	±	0.0059
hellaswag	Yaml	none	acc	0.6397	±	0.0048
		none	acc_norm	0.8268	±	0.0038
openbookqa	Yaml	none	acc	0.3380	±	0.0212
		none	acc_norm	0.4660	±	0.0223
piqa	Yaml	none	acc	0.8139	±	0.0091
		none	acc_norm	0.8205	±	0.0090
winogrande	Yaml	none	acc	0.7609	±	0.0120

📚 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: 2

Safetensors

Model size

19B params

Tensor type

BF16

Collection including macadeliccc/SOLAR-10.7x2_19B

SOLAR-MoE

Collection

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

Paper for macadeliccc/SOLAR-10.7x2_19B

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

Paper • 2312.15166 • Published Dec 23, 2023 • 62