Instructions to use TroyDoesAI/Mermaid_10.5B_cmds with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TroyDoesAI/Mermaid_10.5B_cmds with Transformers:

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

pipe = pipeline("text-generation", model="TroyDoesAI/Mermaid_10.5B_cmds")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TroyDoesAI/Mermaid_10.5B_cmds")
model = AutoModelForCausalLM.from_pretrained("TroyDoesAI/Mermaid_10.5B_cmds")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TroyDoesAI/Mermaid_10.5B_cmds with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TroyDoesAI/Mermaid_10.5B_cmds"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TroyDoesAI/Mermaid_10.5B_cmds",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TroyDoesAI/Mermaid_10.5B_cmds

SGLang

How to use TroyDoesAI/Mermaid_10.5B_cmds 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 "TroyDoesAI/Mermaid_10.5B_cmds" \
    --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": "TroyDoesAI/Mermaid_10.5B_cmds",
		"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 "TroyDoesAI/Mermaid_10.5B_cmds" \
        --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": "TroyDoesAI/Mermaid_10.5B_cmds",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TroyDoesAI/Mermaid_10.5B_cmds with Docker Model Runner:
```
docker model run hf.co/TroyDoesAI/Mermaid_10.5B_cmds
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Mermaid Lab

Experiment:

This experiment aims to enhance language models' functionality by integrating specialized command prompts (!commands) to facilitate task-specific requests. Our goal is to evaluate the model's capacity to comprehend and execute a diverse array of command tasks, thereby testing the expansive capabilities of Large Language Models (LLMs).

By implementing these commands, we seek to explore the potential for teaching models to perform intricate tasks effectively. Through this endeavor, we aim to push the boundaries of language model versatility and empower them to engage in a broader range of specialized tasks.

!mermaid

# Will generate a mermaid diagram of the above input

"input,output": "%input%\n\n!mermaid\n%output%",

{input}

!mermaid

graph TB;
  .
  .
  .
end

Downloads last month: 2

Safetensors

Model size

11B params

Tensor type

F16

Model tree for TroyDoesAI/Mermaid_10.5B_cmds

Quantizations

1 model