Instructions to use Masterjp123/MythicalMax with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Masterjp123/MythicalMax with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Masterjp123/MythicalMax")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Masterjp123/MythicalMax") model = AutoModelForCausalLM.from_pretrained("Masterjp123/MythicalMax") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Masterjp123/MythicalMax with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Masterjp123/MythicalMax" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Masterjp123/MythicalMax", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Masterjp123/MythicalMax
- SGLang
How to use Masterjp123/MythicalMax 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 "Masterjp123/MythicalMax" \ --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": "Masterjp123/MythicalMax", "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 "Masterjp123/MythicalMax" \ --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": "Masterjp123/MythicalMax", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Masterjp123/MythicalMax with Docker Model Runner:
docker model run hf.co/Masterjp123/MythicalMax
Commit ·
22cde33
1
Parent(s): c295773
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,6 @@ pipeline_tag: text-generation
|
|
| 7 |
---
|
| 8 |
This model is a mix of MythosMax-L2-13B and Mythical-Destroyer-V2-L2-13B
|
| 9 |
|
| 10 |
-
It's perpose was to make a mix of Mythical destoryer, MythosMax and Kimiko Lora that could have the best parts of each, NOTE: this model is very exparimental.
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
This model is a mix of MythosMax-L2-13B and Mythical-Destroyer-V2-L2-13B
|
| 9 |
|
| 10 |
+
It's perpose was to make a mix of Mythical destoryer, MythosMax and Kimiko Lora that could have the best parts of each, NOTE: this model is very exparimental.
|
| 11 |
+
|
| 12 |
+
Feel free to make a GPTQ or any other quantized version of this model, becuase I do not plain to.
|