Instructions to use steef68/ATLAS-QUANTUM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use steef68/ATLAS-QUANTUM with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="steef68/ATLAS-QUANTUM", filename="ATLAS-QUANTUM-7B-Uncensored.q2_K.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 steef68/ATLAS-QUANTUM with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf steef68/ATLAS-QUANTUM:Q2_K # Run inference directly in the terminal: llama-cli -hf steef68/ATLAS-QUANTUM:Q2_K
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf steef68/ATLAS-QUANTUM:Q2_K # Run inference directly in the terminal: llama-cli -hf steef68/ATLAS-QUANTUM:Q2_K
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 steef68/ATLAS-QUANTUM:Q2_K # Run inference directly in the terminal: ./llama-cli -hf steef68/ATLAS-QUANTUM:Q2_K
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 steef68/ATLAS-QUANTUM:Q2_K # Run inference directly in the terminal: ./build/bin/llama-cli -hf steef68/ATLAS-QUANTUM:Q2_K
Use Docker
docker model run hf.co/steef68/ATLAS-QUANTUM:Q2_K
- LM Studio
- Jan
- Ollama
How to use steef68/ATLAS-QUANTUM with Ollama:
ollama run hf.co/steef68/ATLAS-QUANTUM:Q2_K
- Unsloth Studio new
How to use steef68/ATLAS-QUANTUM 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 steef68/ATLAS-QUANTUM 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 steef68/ATLAS-QUANTUM to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for steef68/ATLAS-QUANTUM to start chatting
- Docker Model Runner
How to use steef68/ATLAS-QUANTUM with Docker Model Runner:
docker model run hf.co/steef68/ATLAS-QUANTUM:Q2_K
- Lemonade
How to use steef68/ATLAS-QUANTUM with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull steef68/ATLAS-QUANTUM:Q2_K
Run and chat with the model
lemonade run user.ATLAS-QUANTUM-Q2_K
List all available models
lemonade list
Update README.md
#2
by derricka59 - opened
README.md
CHANGED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: llama
|
| 3 |
+
tags:
|
| 4 |
+
- quantization
|
| 5 |
+
- efficient-inference
|
| 6 |
+
- machine-learning
|
| 7 |
+
- language-model
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
datasets:
|
| 10 |
+
- ATLAS-QUANTUM # Replace with actual dataset names
|
| 11 |
+
language: en
|
| 12 |
+
model_architecture: llama
|
| 13 |
+
model_size: 6.74B
|
| 14 |
+
quantization: Q2_K
|
| 15 |
+
inference: true
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
# ATLAS-QUANTUM
|
| 19 |
+
|
| 20 |
+
**Author:** [steef68](https://huggingface.co/steef68)
|
| 21 |
+
**Repository:** [ATLAS-QUANTUM](https://huggingface.co/steef68/ATLAS-QUANTUM)
|
| 22 |
+
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
## Overview
|
| 26 |
+
|
| 27 |
+
ATLAS-QUANTUM is a lightweight and efficient implementation of a LLaMA-based language model. It is optimized for environments requiring high efficiency and reduced computational overhead through 2-bit quantization (Q2_K). This configuration is ideal for fast inference while maintaining quality in natural language processing tasks.
|
| 28 |
+
|
| 29 |
+
### Key Features
|
| 30 |
+
- **Model Size:** 6.74 billion parameters
|
| 31 |
+
- **Quantization:** 2-bit (Q2_K) for compact deployment
|
| 32 |
+
- **Architecture:** LLaMA
|
| 33 |
+
- **Language Support:** English
|
| 34 |
+
- **Purpose:** Inference-ready, suitable for various NLP applications
|
| 35 |
+
|
| 36 |
+
---
|
| 37 |
+
|
| 38 |
+
## Usage
|
| 39 |
+
|
| 40 |
+
To deploy this model or use it in your application, follow the steps below:
|
| 41 |
+
|
| 42 |
+
### Quick Start
|
| 43 |
+
1. **Clone the Repository:**
|
| 44 |
+
```bash
|
| 45 |
+
git clone https://huggingface.co/steef68/ATLAS-QUANTUM
|
| 46 |
+
cd ATLAS-QUANTUM
|
| 47 |
+
|
| 48 |
+
2. Install Dependencies: Install the required libraries. Ensure compatibility with Hugging Face's transformers library.
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
3. Load the Model: Use the following Python code snippet to load and run the model:
|
| 52 |
+
|
| 53 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 54 |
+
|
| 55 |
+
tokenizer = AutoTokenizer.from_pretrained("steef68/ATLAS-QUANTUM")
|
| 56 |
+
model = AutoModelForCausalLM.from_pretrained("steef68/ATLAS-QUANTUM", quantization=True)
|
| 57 |
+
|
| 58 |
+
inputs = tokenizer("Your input text here", return_tensors="pt")
|
| 59 |
+
outputs = model.generate(inputs["input_ids"], max_length=50)
|
| 60 |
+
print(tokenizer.decode(outputs[0]))
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
---
|
| 66 |
+
|
| 67 |
+
Notes and Limitations
|
| 68 |
+
|
| 69 |
+
Runtime Issues: The Hugging Face Space linked to this model has reported runtime errors. If you encounter issues, check your setup and log files.
|
| 70 |
+
|
| 71 |
+
Documentation: The current documentation is under development. Contributions to improve the model card and repository are encouraged.
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
---
|
| 76 |
+
|
| 77 |
+
Resources
|
| 78 |
+
|
| 79 |
+
Model Repository: ATLAS-QUANTUM
|
| 80 |
+
|
| 81 |
+
Hugging Face Space: Atlas-Quantum Space
|
| 82 |
+
|
| 83 |
+
Documentation: Hugging Face Docs
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
---
|
| 88 |
+
|
| 89 |
+
License
|
| 90 |
+
|
| 91 |
+
This model is licensed under the Apache 2.0 License. Please review the terms before use.
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
---
|
| 95 |
+
|
| 96 |
+
Metadata
|
| 97 |
+
|
| 98 |
+
The metadata block at the top ensures compatibility with Hugging Face's model card requirements. Replace placeholders (like <dataset-name>) with the appropriate information if available.
|
| 99 |
+
|
| 100 |
+
### Changes Made
|
| 101 |
+
1. **Added YAML Metadata Block:** This includes necessary fields such as `library-name`, `tags`, `license`, `datasets`, `language`, and model-specific information.
|
| 102 |
+
2. **Expanded README Content:** Included an example for loading the model, clarified runtime issues, and improved formatting.
|
| 103 |
+
3. **Placeholders:** Ensure to replace `model-name` and other placeholders with actual details.
|
| 104 |
+
|
| 105 |
+
|