Instructions to use Lucasgitguy-co/minimind-mermaid-run2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lucasgitguy-co/minimind-mermaid-run2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Lucasgitguy-co/minimind-mermaid-run2")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Lucasgitguy-co/minimind-mermaid-run2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Lucasgitguy-co/minimind-mermaid-run2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Lucasgitguy-co/minimind-mermaid-run2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lucasgitguy-co/minimind-mermaid-run2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Lucasgitguy-co/minimind-mermaid-run2
- SGLang
How to use Lucasgitguy-co/minimind-mermaid-run2 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 "Lucasgitguy-co/minimind-mermaid-run2" \ --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": "Lucasgitguy-co/minimind-mermaid-run2", "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 "Lucasgitguy-co/minimind-mermaid-run2" \ --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": "Lucasgitguy-co/minimind-mermaid-run2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Lucasgitguy-co/minimind-mermaid-run2 with Docker Model Runner:
docker model run hf.co/Lucasgitguy-co/minimind-mermaid-run2
Download docs/PROVENANCE.md from Lucasgitguy-co/minimind-mermaid-run2: direct link, hf CLI and curl.
- Browser
- Download file 1.06 kB
-
https://huggingface.co/Lucasgitguy-co/minimind-mermaid-run2/resolve/main/docs/PROVENANCE.md
- Command line
-
hf download hf://Lucasgitguy-co/minimind-mermaid-run2/docs/PROVENANCE.md
-
curl -L -o PROVENANCE.md https://huggingface.co/Lucasgitguy-co/minimind-mermaid-run2/resolve/main/docs/PROVENANCE.md
Provenance and reproducibility
Repository: Lucasgitguy-co/minimind-mermaid-run2.
Documentation audit: 2026-11-01. Inspected repository revision: 37c3a867ce6cb5020e8095a2309af40ade188e7a.
Upstream model family: jingyaogong/minimind-3.
Original local base revision verified: f92512d4cd6142fa9acc0d6022375049a8974bf6. The cached download revision resolves on the upstream repository and its configuration matches the local training base byte-for-byte.
Evaluation status
No new inference run, benchmark, or training was performed in this documentation update. Existing explicitly documented smoke-test results are retained in the README. The labels Heretic, run2, and trial65 identify releases; they are not quality rankings.
Reproduction gaps
A complete reproduction requires the exact source revision, training-data snapshot and split, training/modification command, dependency versions, seeds, and evaluation outputs. Missing evidence is not filled with inferred benchmark scores.