73 lines
2.0 KiB
Markdown
73 lines
2.0 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
license: mit
|
|
base_model: Abhiray/Sutra-Instruct-350M
|
|
tags:
|
|
- gguf
|
|
- llama.cpp
|
|
- quantized
|
|
- gpt2
|
|
- sutra
|
|
pipeline_tag: text-generation
|
|
library_name: gguf
|
|
---
|
|
|
|
# Sutra-Instruct-350M-GGUF
|
|
|
|
This repository contains the official GGUF quantizations of [**Sutra-Instruct-350M**](https://huggingface.co/Abhiray/Sutra-Instruct-350M), a 350-million parameter model trained entirely from scratch by Abhiray.
|
|
|
|
The **Sutra** (सूत्र) series is designed to be a high-speed, rule-based instruction model. These GGUF versions are optimized for ultra-low latency inference on consumer-grade hardware, including CPUs and mobile devices.
|
|
|
|
---
|
|
|
|
## 📁 Available Quantizations
|
|
|
|
| File Name | Quant Method | Size | Description |
|
|
| :--- | :--- | :--- | :--- |
|
|
| **sutra-fp16.gguf** | None (F16) | ~779 MB | Original weights. RECOMMENDED MOST Best for maximum quality and accuracy. |
|
|
| **sutra-Q8_0.gguf** | Q8_0 | ~417 MB | Standard 8-bit. Near-lossless; RECOMMENDED for most users. |
|
|
| **sutra-Q4_K_M.gguf** | Q4_K_M | ~258 MB | 4-bit Medium. Its for just testing not recommended much. |
|
|
|
|
---
|
|
|
|
## 🚀 Quick Start (Inference)
|
|
|
|
### 1. Using llama.cpp
|
|
Run the model directly from your terminal using `llama-cli`:
|
|
|
|
```bash
|
|
./llama-cli -m sutra-Q8_0.gguf -p "Instruction: What is the law of gravity?\n\nResponse:" -n 400 --temp 0.55 --repeat-penalty 1.2
|
|
```
|
|
|
|
### 2. Using Ollama (Plug-and-Play)
|
|
To use this with Ollama, create a file named Modelfile with the following content:
|
|
|
|
FROM ./sutra-Q8_0.gguf
|
|
TEMPLATE """Instruction:
|
|
{{ .Prompt }}
|
|
|
|
Response:
|
|
"""
|
|
PARAMETER stop "Instruction:"
|
|
PARAMETER stop "\nInstruction:"
|
|
PARAMETER temperature 0.55
|
|
PARAMETER repeat_penalty 1.2
|
|
PARAMETER top_k 50
|
|
PARAMETER num_predict 512
|
|
|
|
Then, initialize and run the model:
|
|
|
|
ollama create sutra -f Modelfile
|
|
ollama run sutra
|
|
|
|
⚙️ Optimized Settings
|
|
To prevent the model from looping or hallucinating, we strongly recommend these inference parameters:
|
|
|
|
Temperature: 0.55
|
|
|
|
Repeat Penalty: 1.2
|
|
|
|
Top-K: 50
|
|
|
|
Max Tokens: 512 |