Text Generation
Transformers
Safetensors
mistral
Roleplay
Uncensored
Storyteller
text-generation-inference
Instructions to use IIEleven11/Kalypso with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IIEleven11/Kalypso with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="IIEleven11/Kalypso")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("IIEleven11/Kalypso") model = AutoModelForCausalLM.from_pretrained("IIEleven11/Kalypso") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use IIEleven11/Kalypso with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IIEleven11/Kalypso" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IIEleven11/Kalypso", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/IIEleven11/Kalypso
- SGLang
How to use IIEleven11/Kalypso 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 "IIEleven11/Kalypso" \ --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": "IIEleven11/Kalypso", "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 "IIEleven11/Kalypso" \ --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": "IIEleven11/Kalypso", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use IIEleven11/Kalypso with Docker Model Runner:
docker model run hf.co/IIEleven11/Kalypso
Update README.md
Browse files
README.md
CHANGED
|
@@ -880,10 +880,10 @@ a:hover .link-arrow {
|
|
| 880 |
<div class="template-card">
|
| 881 |
<div class="template-item">
|
| 882 |
<div class="template-content">
|
| 883 |
-
<a href="https://huggingface.co/IIEleven11/
|
| 884 |
Kalypso Sampler Settings
|
| 885 |
<span class="link-arrow">→</span>
|
| 886 |
-
<span class="template-description">Use with
|
| 887 |
</a>
|
| 888 |
</div>
|
| 889 |
</div>
|
|
|
|
| 880 |
<div class="template-card">
|
| 881 |
<div class="template-item">
|
| 882 |
<div class="template-content">
|
| 883 |
+
<a href="https://huggingface.co/IIEleven11/Kalypso/blob/main/Mistral%2520V7-Tekken.json" target="_blank" class="template-link">
|
| 884 |
Kalypso Sampler Settings
|
| 885 |
<span class="link-arrow">→</span>
|
| 886 |
+
<span class="template-description">Use with Mistral Tekken V7</span>
|
| 887 |
</a>
|
| 888 |
</div>
|
| 889 |
</div>
|