Instructions to use RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf: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 RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf: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 RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/STEM-AI-mtl_-_phi-2-electrical-engineering-gguf:Q4_K_M

Run and chat with the model

lemonade run user.STEM-AI-mtl_-_phi-2-electrical-engineering-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

phi-2-electrical-engineering - GGUF

Model creator: https://huggingface.co/STEM-AI-mtl/
Original model: https://huggingface.co/STEM-AI-mtl/phi-2-electrical-engineering/

Name	Quant method	Size
phi-2-electrical-engineering.Q2_K.gguf	Q2_K	1.01GB
phi-2-electrical-engineering.IQ3_XS.gguf	IQ3_XS	1.14GB
phi-2-electrical-engineering.IQ3_S.gguf	IQ3_S	1.16GB
phi-2-electrical-engineering.Q3_K_S.gguf	Q3_K_S	1.16GB
phi-2-electrical-engineering.IQ3_M.gguf	IQ3_M	1.28GB
phi-2-electrical-engineering.Q3_K.gguf	Q3_K	1.38GB
phi-2-electrical-engineering.Q3_K_M.gguf	Q3_K_M	1.38GB
phi-2-electrical-engineering.Q3_K_L.gguf	Q3_K_L	1.49GB
phi-2-electrical-engineering.IQ4_XS.gguf	IQ4_XS	1.43GB
phi-2-electrical-engineering.Q4_0.gguf	Q4_0	1.49GB
phi-2-electrical-engineering.IQ4_NL.gguf	IQ4_NL	1.5GB
phi-2-electrical-engineering.Q4_K_S.gguf	Q4_K_S	1.5GB
phi-2-electrical-engineering.Q4_K.gguf	Q4_K	1.67GB
phi-2-electrical-engineering.Q4_K_M.gguf	Q4_K_M	1.67GB
phi-2-electrical-engineering.Q4_1.gguf	Q4_1	1.65GB
phi-2-electrical-engineering.Q5_0.gguf	Q5_0	1.8GB
phi-2-electrical-engineering.Q5_K_S.gguf	Q5_K_S	1.8GB
phi-2-electrical-engineering.Q5_K.gguf	Q5_K	1.93GB
phi-2-electrical-engineering.Q5_K_M.gguf	Q5_K_M	1.93GB
phi-2-electrical-engineering.Q5_1.gguf	Q5_1	1.95GB
phi-2-electrical-engineering.Q6_K.gguf	Q6_K	2.13GB
phi-2-electrical-engineering.Q8_0.gguf	Q8_0	2.75GB

Original model description:

license: other license_name: stem.ai.mtl license_link: LICENSE language: - en tags: - phi-2 - electrical engineering - Microsoft datasets: - STEM-AI-mtl/Electrical-engineering - garage-bAInd/Open-Platypus task_categories: - question-answering - text-generation pipeline_tag: text-generation widget: - text: "Enter your instruction here" inference: true auto_sample: true inference_code: chat-GPTQ.py library_tag: transformers

For the electrical engineering community

A unique, deployable and efficient 2.7 billion parameters model in the field of electrical engineering. This repo contains the adapters from the LoRa fine-tuning of the phi-2 model from Microsoft. It was trained on the STEM-AI-mtl/Electrical-engineering dataset combined with garage-bAInd/Open-Platypus.

Developed by: STEM.AI
Model type: Q&A and code generation
Language(s) (NLP): English
Finetuned from model: microsoft/phi-2

Direct Use

Q&A related to electrical engineering, and Kicad software. Creation of Python code in general, and for Kicad's scripting console.

Refer to microsoft/phi-2 model card for recommended prompt format.

Inference script

Standard

GPTQ format

Training Details

Training Data

Dataset related to electrical engineering: STEM-AI-mtl/Electrical-engineering It is composed of queries, 65% about general electrical engineering, 25% about Kicad (EDA software) and 10% about Python code for Kicad's scripting console.

In additionataset related to STEM and NLP: garage-bAInd/Open-Platypus

Training Procedure

LoRa script

A LoRa PEFT was performed on a 48 Gb A40 Nvidia GPU.

Model Card Authors

STEM.AI: stem.ai.mtl@gmail.com
William Harbec

Downloads last month: 588

GGUF

Model size

3B params

Architecture

phi2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support