Instructions to use Gemstone-Models-Cooldown/Gemstone-256x27_cooldown with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gemstone-Models-Cooldown/Gemstone-256x27_cooldown with Transformers:

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

pipe = pipeline("text-generation", model="Gemstone-Models-Cooldown/Gemstone-256x27_cooldown")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gemstone-Models-Cooldown/Gemstone-256x27_cooldown")
model = AutoModelForCausalLM.from_pretrained("Gemstone-Models-Cooldown/Gemstone-256x27_cooldown", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gemstone-Models-Cooldown/Gemstone-256x27_cooldown with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gemstone-Models-Cooldown/Gemstone-256x27_cooldown"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Gemstone-Models-Cooldown/Gemstone-256x27_cooldown",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Gemstone-Models-Cooldown/Gemstone-256x27_cooldown

SGLang

How to use Gemstone-Models-Cooldown/Gemstone-256x27_cooldown 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 "Gemstone-Models-Cooldown/Gemstone-256x27_cooldown" \
    --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": "Gemstone-Models-Cooldown/Gemstone-256x27_cooldown",
		"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 "Gemstone-Models-Cooldown/Gemstone-256x27_cooldown" \
        --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": "Gemstone-Models-Cooldown/Gemstone-256x27_cooldown",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Gemstone-Models-Cooldown/Gemstone-256x27_cooldown with Docker Model Runner:
```
docker model run hf.co/Gemstone-Models-Cooldown/Gemstone-256x27_cooldown
```

smcleish commited on Feb 7, 2025

Commit

17a366b

verified ·

1 Parent(s): d66626d

Update README

Browse files

Files changed (1) hide show

README.md +26 -5

README.md CHANGED Viewed

@@ -9,10 +9,31 @@ datasets:
 - allenai/dolma
 ---
-## Model Details
-### Training
-Models trained using [litgpt](https://github.com/Lightning-AI/litgpt) and [AxoNN](https://github.com/axonn-ai/litgpt) on AMD MI250 GPUs.
-### Data
-Train and validation data is taken from non-overlapping subsets of [dolma](https://huggingface.co/datasets/allenai/dolma).

 - allenai/dolma
 ---
+# Gemstone-256x27_cooldown
+Gemstone-256x27_cooldown is part of the [Gemstone Suite of Models](https://huggingface.co/collections/tomg-group-umd/gemstone-models-679408ee3f19f1d4d00e8b10). A set of models trained with varying widths and depths. This model has had its learning rate linearly decreased to 0 over 10% of the current training tokens, over token counts from 10 to 100 billion.
+Revisions are named "step\_{x}\_cooldown\_{y}" where x is the step count when we began the cooldown, and y is the current step count. The main branch is the last cooldown for this model which is a cooldown from 100 billion tokens to 110 billion tokens.
+## Training
+We train using [litgpt](https://github.com/Lightning-AI/litgpt) and [AxoNN](https://github.com/axonn-ai/litgpt) using AMD MI250X GPUs on [Frontier](https://www.olcf.ornl.gov/olcf-resources/compute-systems/frontier/) at Oak Ridge National Laboratory with a global batch size of 2048.
+## Data
+Train and validation data is taken from non-overlapping subsets of [dolma](https://huggingface.co/datasets/allenai/dolma). As such it is _not_ an instruction model.
+## Using Gemstone-256x27_cooldown
+The Gemstones are based on the [gemma-2b](https://huggingface.co/google/gemma-2b) architecture and use [modeling_gemma.py](https://github.com/huggingface/transformers/blob/main/src/transformers/models/gemma/modeling_gemma.py) to run using the transformers library.
+## Licence
+This model is released under the [apache-2.0](https://choosealicense.com/licenses/apache-2.0/) licence.
+## Contact
+Please, feel free to contact us with any questions, or open a discussion thread.
+# Citation
+```
+@article{mcleish2024gemstones
+    title={Gemstones: A Model Suite for Multi-Faceted Scaling Laws},
+    author={Sean McLeish and John Kirchenbauer and David Yu Miller and Siddharth Singh and Abhinav Bhatele and Micah Goldblum and Ashwinee Panda and Tom Goldstein},
+    journal={arXiv preprint arXiv:2502.},
+    year={2025}
+}
+```