Instructions to use Gryphe/MythoBoros-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Gryphe/MythoBoros-13b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Gryphe/MythoBoros-13b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Gryphe/MythoBoros-13b") model = AutoModelForCausalLM.from_pretrained("Gryphe/MythoBoros-13b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Gryphe/MythoBoros-13b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Gryphe/MythoBoros-13b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gryphe/MythoBoros-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Gryphe/MythoBoros-13b
- SGLang
How to use Gryphe/MythoBoros-13b 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 "Gryphe/MythoBoros-13b" \ --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": "Gryphe/MythoBoros-13b", "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 "Gryphe/MythoBoros-13b" \ --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": "Gryphe/MythoBoros-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Gryphe/MythoBoros-13b with Docker Model Runner:
docker model run hf.co/Gryphe/MythoBoros-13b
| license: other | |
| language: | |
| - en | |
| ## Model details | |
| MythoBoros-13b can be considered a sister model to [MythoLogic-13b](https://huggingface.co/Gryphe/MythoLogic-13b), sharing the same goals but having a different approach. | |
| Whereas the previous model was a series of experimental gradient merges, this one is a simple straight-up 66/34 merge of [Chronos](https://huggingface.co/elinas/chronos-13b) and the freshly released [Ouroboros](https://huggingface.co/CalderaAI/13B-Ouroboros), providing a very solid foundation for a well-performing roleplaying model. | |
| MythoBoros tends to be somewhat more formal with its responses in comparison to MythoLogic. | |
| My advice? Try both, see which one you prefer. | |
| Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheBloke/MythoBoros-13B-GGML) - [GPTQ](https://huggingface.co/TheBloke/MythoBoros-13B-GPTQ) (You're the best!) | |
| ## Prompt Format | |
| This model works best with Alpaca formatting, so for optimal model performance, use: | |
| ``` | |
| <System prompt/Character Card> | |
| ### Instruction: | |
| Your instruction or question here. | |
| For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only. | |
| ### Response: | |
| ``` |