Instructions to use MarshallDoyle/NASA-Systems-Engineering with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MarshallDoyle/NASA-Systems-Engineering with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MarshallDoyle/NASA-Systems-Engineering", dtype="auto")

llama-cpp-python

How to use MarshallDoyle/NASA-Systems-Engineering with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MarshallDoyle/NASA-Systems-Engineering",
	filename="unsloth.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use MarshallDoyle/NASA-Systems-Engineering with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MarshallDoyle/NASA-Systems-Engineering:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MarshallDoyle/NASA-Systems-Engineering:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MarshallDoyle/NASA-Systems-Engineering:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MarshallDoyle/NASA-Systems-Engineering:Q4_K_M

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 MarshallDoyle/NASA-Systems-Engineering:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf MarshallDoyle/NASA-Systems-Engineering:Q4_K_M

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 MarshallDoyle/NASA-Systems-Engineering:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MarshallDoyle/NASA-Systems-Engineering:Q4_K_M

Use Docker

docker model run hf.co/MarshallDoyle/NASA-Systems-Engineering:Q4_K_M

LM Studio
Jan
Ollama
How to use MarshallDoyle/NASA-Systems-Engineering with Ollama:
```
ollama run hf.co/MarshallDoyle/NASA-Systems-Engineering:Q4_K_M
```

Unsloth Studio new

How to use MarshallDoyle/NASA-Systems-Engineering 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 MarshallDoyle/NASA-Systems-Engineering 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 MarshallDoyle/NASA-Systems-Engineering to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MarshallDoyle/NASA-Systems-Engineering to start chatting

Docker Model Runner
How to use MarshallDoyle/NASA-Systems-Engineering with Docker Model Runner:
```
docker model run hf.co/MarshallDoyle/NASA-Systems-Engineering:Q4_K_M
```

Lemonade

How to use MarshallDoyle/NASA-Systems-Engineering with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MarshallDoyle/NASA-Systems-Engineering:Q4_K_M

Run and chat with the model

lemonade run user.NASA-Systems-Engineering-Q4_K_M

List all available models

lemonade list

MarshallDoyle commited on Jun 10, 2025

Commit

9cfc350

verified ·

1 Parent(s): 46b85e0

Update README.md

Browse files

Files changed (1) hide show

README.md +33 -6

README.md CHANGED Viewed

@@ -11,12 +11,39 @@ language:
 - en
 ---
-# Uploaded  model
-- **Developed by:** MarshallDoyle
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 - en
 ---
+# NASA Systems Engineering LLaMA-3.1 8B Instruct (Fine-Tuned)
+- **Developed by:** MarshallDoyle
+- **License:** Apache-2.0
+- **Fine-tuned from model:** unsloth/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit
+This model specializes in answering questions and summarizing content from NASA’s *Systems Engineering Handbook* (2018) PDF. It was fine-tuned using Hugging Face’s TRL and LoRA techniques for high efficiency.
+## Preview of Fine-Tuning Source
+![Preview of NASA Systems Engineering Handbook first page](https://www.nasa.gov/sites/default/files/atoms/files/nasa_systems_engineering_handbook_0.pdf#page=1)
+*(Above: the front page of the NASA Systems Engineering Handbook used for fine-tuning.)*
+---
+## Overview
+**Key Features:**
+- **Domain Expertise:** Deep understanding of NASA systems engineering lifecycle phases, verification vs. validation testing, and SE best practices.
+- **Compact Footprint:** Keeps the lightweight 8B base model, adding only ~83.8M trainable parameters via LoRA.
+- **Extended Context:** Supports up to 128K tokens for long-form document Q&A.
+**Intended Use:** Ideal for educational tools, engineering Q&A assistants, mission planning support, and rapid handbook lookup.
+---
+## Model Card Updates
+- Removed Unsloth branding badges in favor of a direct preview of the NASA PDF source.
+- Added a representative image of the handbook’s first page to illustrate the training data.
+---
+*