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

Libraries

How to use upstage/SOLAR-10.7B-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-v1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use upstage/SOLAR-10.7B-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-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "upstage/SOLAR-10.7B-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use upstage/SOLAR-10.7B-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-v1.0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "upstage/SOLAR-10.7B-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-v1.0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "upstage/SOLAR-10.7B-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Question about continued training.

#14

by neverdoubt - opened Apr 2, 2024

Discussion

neverdoubt

Apr 2, 2024

Thank you for the sharing a great work.
How many tokens are used for the continued training?

Joseph717171

Apr 2, 2024

•

edited Apr 2, 2024

source: https://arxiv.org/html/2312.15166v2

Joseph717171

Apr 2, 2024

•

edited Apr 2, 2024

Source: https://arxiv.org/html/2312.15166v2

falca

Apr 2, 2024

So by "continued pretraining" you mean instruction tuning? Otherwise can't find info on that either. Would really appreciate if you clarify on that moment a little more.

Joseph717171

Apr 2, 2024

No, for UpStage’s Solar-10.7B, they took base weights, Ups-Scaled them, and then continued pretraining. Pretraining is different than fine-tuning; it requires more data/information than fine-tuning. “2. Depth Up-Scaling”, details the continued pretraining. “3. Training”, details the fine-tuning and instruction tuning. With that being said, perhaps UpStage, can fill in any blanks that we don’t have the information to fill. 🤔

falca

Apr 15, 2024

Yes, I've read that section. Unfortunately, it does not mention anything about data for pretraining: datasets or number of tokens.

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