README.md

---
base_model: stabilityai/stable-code-3b
inference: false
language:
  - en
license: other
license_link: https://huggingface.co/stabilityai/stable-code-3b/blob/main/LICENSE
model_creator: stabilityai
model_name: stable-code-3b
pipeline_tag: text-generation
datasets:
  - tiiuae/falcon-refinedweb
  - bigcode/the-stack-github-issues
  - bigcode/commitpackft
  - bigcode/starcoderdata
  - EleutherAI/proof-pile-2
  - meta-math/MetaMathQA
tags:
  - causal-lm
  - code
quantized_by: brittlewis12
---

# stable-code-3b GGUF

Original model: [stable-code-3b](https://huggingface.co/stabilityai/stable-code-3b)
Model creator: [StabilityAI](https://huggingface.co/stabilityai/stable-code-3b)

This repo contains GGUF format model files for StabilityAI’s stable-code-3b with 16k context.

> stable-code-3b is a 2.7B billion parameter decoder-only language model pre-trained on 1.3 trillion tokens of diverse textual and code datasets. stable-code-3b is trained on 18 programming languages (selected based on the 2023 StackOverflow Developer Survey) and demonstrates state-of-the-art performance (compared to models of similar size) on the MultiPL-E metrics across multiple programming languages tested using BigCode's Evaluation Harness.


### What is GGUF?

GGUF is a file format for representing AI models. It is the third version of the format, introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Converted using llama.cpp build 1897 (revision [2b3a665](https://github.com/ggerganov/llama.cpp/commit/2b3a665))

## Prompt template: Completion or Fill-in-Middle

### Completion

```
{{prompt}}
```

### Fill-in-Middle (FIM)

```
<fim_prefix>{{prefix code}}<fim_suffix>{{suffix code}}<fim_middle>
```

Example prompt with special prefix, suffix, and middle tokens in context:

```
<fim_prefix>def fib(n):
<fim_suffix>
    else:
        return fib(n - 2) + fib(n - 1)
<fim_middle>
```

---

## Download & run with [cnvrs](https://testflight.apple.com/join/sFWReS7K) on iPhone, iPad, and Mac!

[cnvrs](https://testflight.apple.com/join/sFWReS7K) is the best app for private, local AI on your device:
- create & save **Characters** with custom system prompts & temperature settings
- download and experiment with any **GGUF model** you can [find on HuggingFace](https://huggingface.co/models?library=gguf)!
- make it your own with custom **Theme colors**
- powered by Metal ⚡️ & [Llama.cpp](https://github.com/ggerganov/llama.cpp), with **haptics** during response streaming!
- **try it out** yourself today, on [Testflight](https://testflight.apple.com/join/sFWReS7K)!

---

# Original Model Evaluation

![spiderchart](https://huggingface.co/stabilityai/stable-code-3b/raw/main/stable_code_3b_spiderchart.svg)

| Model            | Size | Python | C++  | Javascript | Java | PHP  | Rust |
|------------------|------|--------|------|------------|------|------|------|
| **Stable Code**  | 3B   | 32.4%  | 30.9%| 32.1%      | 32.1%| 24.2%| 23.0%|
| CodeLLama        | 7B   | 30.0%  | 28.2%| 32.5%      | 31.1%| 25.7%| 26.3%|
| Deepseek Coder   | 1.3B | 28.6%  | 29.2%| 28.7%      | 29.0%| 23.6%| 18.5%|
| Wizard Coder     | 3B   | 31.6%  | 25.6%| 26.2%      | 25.8%| 25.3%| 20.4%|
| StarCoder        | 3B   | 21.6%  | 19.8%| 21.5%      | 20.5%| 19.0%| 16.9%|
| Replit Code V1.5 | 3B   | 23.0%  | 25.9%| 26.2%      | 23.6%| 23.2%| 21.5%|
| Deci Coder       | 1B   | 19.1%  | 6.8% | 18.4%      | 16.7%| 2.1% | 1.7% |