Instructions to use liminerity/mistral-box with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use liminerity/mistral-box with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="liminerity/mistral-box")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("liminerity/mistral-box") model = AutoModelForCausalLM.from_pretrained("liminerity/mistral-box") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use liminerity/mistral-box with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "liminerity/mistral-box" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "liminerity/mistral-box", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/liminerity/mistral-box
- SGLang
How to use liminerity/mistral-box 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 "liminerity/mistral-box" \ --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": "liminerity/mistral-box", "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 "liminerity/mistral-box" \ --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": "liminerity/mistral-box", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use liminerity/mistral-box with Docker Model Runner:
docker model run hf.co/liminerity/mistral-box
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
language:
en license: apache-2.0 tags:
text-generation-inference
transformers
unsloth
mistral
trl base_model: unsloth/mistral-7b-bnb-4bit
an attempt at making a working "program" inside an llm thru fine tuning. kinda works kinda doesn't
commands are:
start/start box/box
up/down/left/right
heres an example convo:
- user: "start box"
- ai: "```
12345_____1|X....|2|.....|3|.....|4|.....|5|.....|_____```start"- user: "right"
- ai: "right
```12345_____1|.X...|2|.....|3|.....|4|.....|5|.....|_____```"- user: "down"
- ai: "down
```12345_____1|.....|2|.X...|3|.....|4|.....|5|.....|_____```"- user: "right"
- ai: "right
```12345_____1|.....|2|..X..|3|.....|4|.....|5|.....|_____```"- user: "up"
- ai: "up
```12345_____1|..X..|2|.....|3|.....|4|.....|5|.....|_____```"- user: "left"
- ai: "left
error: unable to move left from this position```12345_____1|..X..|2|.....|3|.....|4|.....|5|.....|_____```"
after this it stopped working but you get the gist. imagine playing doom thrun an llm lol
Uploaded model
- Developed by: liminerity
- License: apache-2.0
- Finetuned from model : unsloth/mistral-7b-bnb-4bit
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 6

docker model run hf.co/liminerity/mistral-box