Instructions to use upstage/SOLAR-10.7B-Instruct-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use upstage/SOLAR-10.7B-Instruct-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="upstage/SOLAR-10.7B-Instruct-v1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("upstage/SOLAR-10.7B-Instruct-v1.0")
model = AutoModelForCausalLM.from_pretrained("upstage/SOLAR-10.7B-Instruct-v1.0")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use upstage/SOLAR-10.7B-Instruct-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "upstage/SOLAR-10.7B-Instruct-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "upstage/SOLAR-10.7B-Instruct-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/upstage/SOLAR-10.7B-Instruct-v1.0

SGLang

How to use upstage/SOLAR-10.7B-Instruct-v1.0 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 "upstage/SOLAR-10.7B-Instruct-v1.0" \
    --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": "upstage/SOLAR-10.7B-Instruct-v1.0",
		"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 "upstage/SOLAR-10.7B-Instruct-v1.0" \
        --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": "upstage/SOLAR-10.7B-Instruct-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use upstage/SOLAR-10.7B-Instruct-v1.0 with Docker Model Runner:
```
docker model run hf.co/upstage/SOLAR-10.7B-Instruct-v1.0
```

Does this model support multi-turn conversations?

#18

by apepkuss79 - opened Dec 30, 2023

Discussion

apepkuss79

Dec 30, 2023

If the model supports multi-turn conversations, what does the prompt string look like? Could you please provide an example? Thanks a lot! Happy New Year!

dagelf

Jan 2, 2024

The default llama.cpp server command's webserver's default settings work perfectly for chat, and this model is really good at chat and one of the cleanest ("safe in a non-obnoxious way") bots out, even at high quantization. (Note you have to use GGUF files for llama.cpp, quantize them with the bundled quantize command or just download them from TheBloke's repo)

apepkuss79

Jan 3, 2024

@dagelf Thanks for the reply. We've already supported this model in llama-api-server and llama-chat.

apepkuss79 changed discussion status to closed Jan 3, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment