Instructions to use TeeZee/GALAXY_v03_slimorca_1_epoch_50k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeeZee/GALAXY_v03_slimorca_1_epoch_50k with Transformers:

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

pipe = pipeline("text-generation", model="TeeZee/GALAXY_v03_slimorca_1_epoch_50k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TeeZee/GALAXY_v03_slimorca_1_epoch_50k")
model = AutoModelForCausalLM.from_pretrained("TeeZee/GALAXY_v03_slimorca_1_epoch_50k")
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 TeeZee/GALAXY_v03_slimorca_1_epoch_50k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TeeZee/GALAXY_v03_slimorca_1_epoch_50k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TeeZee/GALAXY_v03_slimorca_1_epoch_50k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TeeZee/GALAXY_v03_slimorca_1_epoch_50k

SGLang

How to use TeeZee/GALAXY_v03_slimorca_1_epoch_50k 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_v03_slimorca_1_epoch_50k" \
    --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": "TeeZee/GALAXY_v03_slimorca_1_epoch_50k",
		"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 "TeeZee/GALAXY_v03_slimorca_1_epoch_50k" \
        --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": "TeeZee/GALAXY_v03_slimorca_1_epoch_50k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TeeZee/GALAXY_v03_slimorca_1_epoch_50k with Docker Model Runner:
```
docker model run hf.co/TeeZee/GALAXY_v03_slimorca_1_epoch_50k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

TeeZee/GALAXY-XB-v1.03

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

Technical notes:

model v03 finetuned on 50k entries from SlimOrca dataset
12 layers removed from both models, 4 more than in original paper but its 1/4 of all layers(48) as per original paper.
base version of upstage/SOLAR-10.7B-v1.0 used for merge

To evaluate

model performance after finetuning, did it recover initial performance loss after merge?

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	57.04
AI2 Reasoning Challenge (25-Shot)	62.71
HellaSwag (10-Shot)	84.58
MMLU (5-Shot)	65.17
TruthfulQA (0-shot)	47.30
Winogrande (5-shot)	82.48
GSM8k (5-shot)	0.00

Downloads last month: 85

Safetensors

Model size

16B params

Tensor type

BF16

Model tree for TeeZee/GALAXY_v03_slimorca_1_epoch_50k

Quantizations

1 model

Dataset used to train TeeZee/GALAXY_v03_slimorca_1_epoch_50k

Collection including TeeZee/GALAXY_v03_slimorca_1_epoch_50k

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

62.710
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

84.580
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

65.170
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

47.300
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

82.480
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

0.000