Instructions to use Heralax/Mistrilitary-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Heralax/Mistrilitary-7b with Transformers:

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

pipe = pipeline("text-generation", model="Heralax/Mistrilitary-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Heralax/Mistrilitary-7b")
model = AutoModelForCausalLM.from_pretrained("Heralax/Mistrilitary-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use Heralax/Mistrilitary-7b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Heralax/Mistrilitary-7b",
	filename="army-pretrain-7.2B-1-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Heralax/Mistrilitary-7b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Heralax/Mistrilitary-7b:F16
# Run inference directly in the terminal:
llama-cli -hf Heralax/Mistrilitary-7b:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Heralax/Mistrilitary-7b:F16
# Run inference directly in the terminal:
llama-cli -hf Heralax/Mistrilitary-7b:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Heralax/Mistrilitary-7b:F16
# Run inference directly in the terminal:
./llama-cli -hf Heralax/Mistrilitary-7b:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Heralax/Mistrilitary-7b:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Heralax/Mistrilitary-7b:F16

Use Docker

docker model run hf.co/Heralax/Mistrilitary-7b:F16

LM Studio
Jan

vLLM

How to use Heralax/Mistrilitary-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Heralax/Mistrilitary-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Heralax/Mistrilitary-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Heralax/Mistrilitary-7b:F16

SGLang

How to use Heralax/Mistrilitary-7b 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 "Heralax/Mistrilitary-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Heralax/Mistrilitary-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Heralax/Mistrilitary-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Heralax/Mistrilitary-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Heralax/Mistrilitary-7b with Ollama:
```
ollama run hf.co/Heralax/Mistrilitary-7b:F16
```

Unsloth Studio new

How to use Heralax/Mistrilitary-7b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Heralax/Mistrilitary-7b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Heralax/Mistrilitary-7b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Heralax/Mistrilitary-7b to start chatting

Docker Model Runner
How to use Heralax/Mistrilitary-7b with Docker Model Runner:
```
docker model run hf.co/Heralax/Mistrilitary-7b:F16
```

Lemonade

How to use Heralax/Mistrilitary-7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Heralax/Mistrilitary-7b:F16

Run and chat with the model

lemonade run user.Mistrilitary-7b-F16

List all available models

lemonade list

Was torn between calling it MiLLM and Mistrillitary. Sigh naming is one of the two great problems in computer science...

This is a domain-expert finetune based on the US Army field manuals (the ones that are published and available for civvies like me). It's focused on factual question answer only, but seems to be able to answer slightly deeper questions in a pinch.

Model Quirks

I had to focus on the army field manuals because the armed forces publishes a truly massive amount of text.
No generalist assistant data was included, which means this is very very very focused on QA, and may be inflexible.
Experimental change: data was mostly generated by a smaller model, Mistral NeMo. Quality seems unaffected, costs are much lower. Had problems with the open-ended questions not being in the right format.
Low temperture recommended. Screenshots use 0.
ChatML
No special tokens added.

Examples:

)