Instructions to use TeeZee/GALAXY-XB-v.02 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeeZee/GALAXY-XB-v.02 with Transformers:

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

pipe = pipeline("text-generation", model="TeeZee/GALAXY-XB-v.02")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TeeZee/GALAXY-XB-v.02")
model = AutoModelForCausalLM.from_pretrained("TeeZee/GALAXY-XB-v.02")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TeeZee/GALAXY-XB-v.02 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TeeZee/GALAXY-XB-v.02"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TeeZee/GALAXY-XB-v.02",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TeeZee/GALAXY-XB-v.02

SGLang

How to use TeeZee/GALAXY-XB-v.02 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 "TeeZee/GALAXY-XB-v.02" \
    --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": "TeeZee/GALAXY-XB-v.02",
		"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 "TeeZee/GALAXY-XB-v.02" \
        --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": "TeeZee/GALAXY-XB-v.02",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TeeZee/GALAXY-XB-v.02 with Docker Model Runner:
```
docker model run hf.co/TeeZee/GALAXY-XB-v.02
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

TeeZee/GALAXY-XB-v.02

Experiment, can DUS be taken one or more steps further?

Technical notes:

10 layers removed from both models this time, 2 more than in original paper.
base version of upstage/SOLAR-10.7B-v1.0 used for merge
no finetuning done yet, this is just a merge, first step in DUS paper
next step, if evaluation proves that its at least as 'smart' as base model, should be finetuning to 'recover' after merge

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	62.48
AI2 Reasoning Challenge (25-Shot)	60.67
HellaSwag (10-Shot)	83.27
MMLU (5-Shot)	64.99
TruthfulQA (0-shot)	43.60
Winogrande (5-shot)	80.27
GSM8k (5-shot)	42.08

Downloads last month: 95

Safetensors

Model size

17B params

Tensor type

BF16

Model tree for TeeZee/GALAXY-XB-v.02

Quantizations

2 models

Collection including TeeZee/GALAXY-XB-v.02

Workbench

Collection

Untested and unfinished models. Works in progress. • 8 items • Updated Apr 16, 2024

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

60.670
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

83.270
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

64.990
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

43.600
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

80.270
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

42.080