Instructions to use Gemstone-Models/Gemstone-2560x8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gemstone-Models/Gemstone-2560x8 with Transformers:

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

pipe = pipeline("text-generation", model="Gemstone-Models/Gemstone-2560x8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gemstone-Models/Gemstone-2560x8")
model = AutoModelForCausalLM.from_pretrained("Gemstone-Models/Gemstone-2560x8", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gemstone-Models/Gemstone-2560x8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gemstone-Models/Gemstone-2560x8"
# 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-2560x8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Gemstone-Models/Gemstone-2560x8

SGLang

How to use Gemstone-Models/Gemstone-2560x8 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-2560x8" \
    --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-2560x8",
		"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-2560x8" \
        --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-2560x8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Gemstone-Models/Gemstone-2560x8 with Docker Model Runner:
```
docker model run hf.co/Gemstone-Models/Gemstone-2560x8
```

I think the upload failed

by mradermacher - opened Feb 7, 2025

Discussion

mradermacher

Feb 7, 2025

Or at least, the files are missing.

smcleish

Gemstones 💎: A Model Suite for Multi-Faceted Scaling Laws org Feb 7, 2025

Hi, the models are being pushed currently. We're aware theres some gaps and trying to smooth them over. It appears most of the steps (stored as revisions) for this model pushed but the last one, we'll be sure fill this.

smcleish changed discussion status to closed Feb 7, 2025

smcleish

Gemstones 💎: A Model Suite for Multi-Faceted Scaling Laws org Feb 8, 2025

Final checkpoint should be available now, sorry for the delay.

mradermacher

Feb 8, 2025

No issue, and thanks for reacting so fast. In case you wonder, I am trying to provide quantized gguf versions of all the gemstone models.

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