Instructions to use Gemstone-Models/Gemstone-256x27 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gemstone-Models/Gemstone-256x27 with Transformers:

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

pipe = pipeline("text-generation", model="Gemstone-Models/Gemstone-256x27")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gemstone-Models/Gemstone-256x27")
model = AutoModelForCausalLM.from_pretrained("Gemstone-Models/Gemstone-256x27", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gemstone-Models/Gemstone-256x27 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gemstone-Models/Gemstone-256x27"
# 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/Gemstone-256x27",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Gemstone-Models/Gemstone-256x27

SGLang

How to use Gemstone-Models/Gemstone-256x27 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/Gemstone-256x27" \
    --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/Gemstone-256x27",
		"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/Gemstone-256x27" \
        --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/Gemstone-256x27",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Gemstone-Models/Gemstone-256x27 with Docker Model Runner:
```
docker model run hf.co/Gemstone-Models/Gemstone-256x27
```

smcleish commited on Feb 9, 2025

Commit

d2ccc1e

verified ·

1 Parent(s): 3a7c576

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -9,8 +9,8 @@ datasets:
 - allenai/dolma
 ---
-# Gemstone-256x27
-Gemstone-256x27 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.
 ## 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.
@@ -19,7 +19,7 @@ We train using [litgpt](https://github.com/Lightning-AI/litgpt) and [AxoNN](http
 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.
 This model is trained for 350 billion tokens, we upload checkpoints every 2 billion tokens (477 steps).
-## Using Gemstone-256x27
 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

 - allenai/dolma
 ---
+# Gemstone-256x23
+Gemstone-256x23 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.
 ## 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.
 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.
 This model is trained for 350 billion tokens, we upload checkpoints every 2 billion tokens (477 steps).
+## Using Gemstone-256x23
 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