Instructions to use Kquant03/EarthRender-32x7B-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kquant03/EarthRender-32x7B-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="Kquant03/EarthRender-32x7B-bf16", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kquant03/EarthRender-32x7B-bf16")
model = AutoModelForCausalLM.from_pretrained("Kquant03/EarthRender-32x7B-bf16", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kquant03/EarthRender-32x7B-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kquant03/EarthRender-32x7B-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kquant03/EarthRender-32x7B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kquant03/EarthRender-32x7B-bf16

SGLang

How to use Kquant03/EarthRender-32x7B-bf16 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 "Kquant03/EarthRender-32x7B-bf16" \
    --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": "Kquant03/EarthRender-32x7B-bf16",
		"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 "Kquant03/EarthRender-32x7B-bf16" \
        --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": "Kquant03/EarthRender-32x7B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kquant03/EarthRender-32x7B-bf16 with Docker Model Runner:
```
docker model run hf.co/Kquant03/EarthRender-32x7B-bf16
```

Kquant03 commited on Jan 5, 2024

Commit

a1f8505

1 Parent(s): 8007862

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -1

README.md CHANGED Viewed

@@ -43,4 +43,9 @@ If all our tokens are sent to just a few popular experts, that will make trainin
 ## "Wait...but you called this a frankenMoE?"
-The difference between MoE and "frankenMoE" lies in the fact that the router layer in a model like the one on this repo is not trained simultaneously. There are rumors about someone developing a way for us to unscuff these frankenMoE models by training the router layer simultaneously. For now, frankenMoE remains psychotic...at least...until now.

 ## "Wait...but you called this a frankenMoE?"
+The difference between MoE and "frankenMoE" lies in the fact that the router layer in a model like the one on this repo is not trained simultaneously. There are rumors about someone developing a way for us to unscuff these frankenMoE models by training the router layer simultaneously. For now, frankenMoE remains psychotic...at least...until now.
+This model is probably the highest performing model on the site, but considering even I, the person who created it, only have 12 gigs of VRAM...only the truly insane will even be capable of controlling the Earth Render.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/xayrIkbnNRJ4WJbdhhRsP.png)
+## this response took about 2 and a half hours lol...