Instructions to use Heralax/Augmental-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Heralax/Augmental-13b with Transformers:

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

pipe = pipeline("text-generation", model="Heralax/Augmental-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Heralax/Augmental-13b")
model = AutoModelForCausalLM.from_pretrained("Heralax/Augmental-13b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Heralax/Augmental-13b 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 Heralax/Augmental-13b
# Run inference directly in the terminal:
llama cli -hf Heralax/Augmental-13b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Heralax/Augmental-13b
# Run inference directly in the terminal:
llama cli -hf Heralax/Augmental-13b

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/Augmental-13b
# Run inference directly in the terminal:
./llama-cli -hf Heralax/Augmental-13b

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/Augmental-13b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Heralax/Augmental-13b

Use Docker

docker model run hf.co/Heralax/Augmental-13b

LM Studio
Jan

vLLM

How to use Heralax/Augmental-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Heralax/Augmental-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Heralax/Augmental-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Heralax/Augmental-13b

SGLang

How to use Heralax/Augmental-13b 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/Augmental-13b" \
    --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": "Heralax/Augmental-13b",
		"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 "Heralax/Augmental-13b" \
        --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": "Heralax/Augmental-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Heralax/Augmental-13b with Ollama:
```
ollama run hf.co/Heralax/Augmental-13b
```
Unsloth Desktop
Docker Model Runner
How to use Heralax/Augmental-13b with Docker Model Runner:
```
docker model run hf.co/Heralax/Augmental-13b
```

Lemonade

How to use Heralax/Augmental-13b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Heralax/Augmental-13b

Run and chat with the model

lemonade run user.Augmental-13b-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

Delete README.md

by Ahsan254 - opened Feb 20, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-258

Ahsan254

Feb 20, 2024

Subject: Proposal for Node.js Developer Position

Dear [Client's Name],

I am writing to express my interest in the Node.js Developer position within your esteemed organization, as advertised. With a solid foundation in Node.js and its associated technologies, coupled with a passion for developing scalable and efficient server-side applications, I am excited about the opportunity to contribute to your team and help drive your projects towards success.

Professional Background:

I bring [X] years of hands-on experience in software development, with a specific focus on Node.js and its popular frameworks such as Express. Throughout my career, I have been involved in the full lifecycle of application development, from conceptualization and design to deployment and maintenance, ensuring that all applications meet the highest standards of quality and performance.

Technical Skills:

Node.js & Frameworks: Proficient in building fast and scalable server-side applications using Node.js. I have extensive experience with Express, which has enabled me to efficiently handle numerous asynchronous operations and improve the overall performance of web applications.
Database Technologies: Skilled in using MongoDB, I have designed and implemented robust data storage solutions that ensure data integrity and support complex queries for real-time access.
RESTful API Development: Experienced in developing and integrating RESTful APIs, facilitating seamless communication between client-side and server-side components of applications.
Front-End Technologies: While my primary focus is on server-side development, I possess a strong understanding of front-end technologies, including HTML, CSS, and JavaScript. This comprehensive skill set allows me to contribute to and collaborate effectively with front-end development teams.
Version Control: Proficient in using Git, I have consistently ensured that all code changes are tracked and managed efficiently, facilitating team collaboration and code integrity.
Problem-Solving & Debugging: Known for my analytical skills and a methodical approach to debugging, I can quickly identify and resolve issues, optimizing application performance and user experience.

How I Can Contribute:

Innovative Solutions: My dedication to staying at the forefront of technology means I am always ready to explore new tools and methodologies to deliver cutting-edge solutions.
Collaborative Approach: Having worked in various cross-functional teams, I understand the importance of collaboration and communication in achieving project goals. I am eager to bring this team-oriented mindset to your projects.
Quality and Efficiency: My commitment to writing clean, testable, and efficient code aligns with your emphasis on quality and attention to detail. I aim to contribute to the development of high-quality applications that meet the needs of your users and stakeholders.

I am enthusiastic about the opportunity to discuss how my background, skills, and enthusiasms align with the needs of your team. I am confident that my contributions will not only meet but exceed your expectations. Thank you for considering my application. I look forward to the possibility of contributing to your team and achieving great success together.

Best regards,

[Your Name]
[Your Contact Information]

Delete README.mdb9a3bb13

Heralax

Owner Feb 20, 2024

The Fuck?!

Heralax changed pull request status to closed Feb 20, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment