Instructions to use ElMater06/SpaceCore with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ElMater06/SpaceCore with Transformers:

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

pipe = pipeline("text-generation", model="ElMater06/SpaceCore")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ElMater06/SpaceCore")
model = AutoModelForCausalLM.from_pretrained("ElMater06/SpaceCore")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ElMater06/SpaceCore with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ElMater06/SpaceCore"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ElMater06/SpaceCore",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ElMater06/SpaceCore

SGLang

How to use ElMater06/SpaceCore 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 "ElMater06/SpaceCore" \
    --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": "ElMater06/SpaceCore",
		"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 "ElMater06/SpaceCore" \
        --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": "ElMater06/SpaceCore",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ElMater06/SpaceCore with Docker Model Runner:
```
docker model run hf.co/ElMater06/SpaceCore
```

ElMater06 commited on May 31, 2023

Commit

3e0b949

1 Parent(s): ab46073

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -9

README.md CHANGED Viewed

@@ -30,17 +30,10 @@ Its the Portal Space Core
 - **License:** [Other]
 - **Finetuned from model [optional]:** [DialoGPT-Small]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
 ## Uses
-The Model Card Kinda Breaks it, I haven't figured out a way to fix it, so if someone knows please send a pull request or a edit or something!
 ### Direct Use

 - **License:** [Other]
 - **Finetuned from model [optional]:** [DialoGPT-Small]
 ## Uses
+The Hosted Inference API Breaks it, I haven't figured out a way to limit its responses so its hard capped at 512 in the Generation_Config.json file. Just change that back to 1024 and you are good
+so if someone knows please send a pull request or a edit or something!
 ### Direct Use