# Bigcode's Starcoder GGML
These files are GGML format model files for [Bigcode's Starcoder](https://huggingface.co/bigcode/starcoder).
Please note that these GGMLs are **not compatible with llama.cpp, or currently with text-generation-webui**. Please see below for a list of tools known to work with these model files.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/starcoder-GPTQ)
* [4, 5, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/starcoder-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/bigcode/starcoder)
## Compatibilty
These files are **not** compatible with llama.cpp.
Currently they can be used with:
* KoboldCpp, a powerful inference engine based on llama.cpp, with good UI: [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* The ctransformers Python library, which includes LangChain support: [ctransformers](https://github.com/marella/ctransformers)
* The GPT4All-UI which uses ctransformers: [GPT4All-UI](https://github.com/ParisNeo/gpt4all-ui)
* [rustformers' llm](https://github.com/rustformers/llm)
* The example `starcoder` binary provided with [ggml](https://github.com/ggerganov/ggml)
As other options become available I will endeavour to update them here (do let me know in the Community tab if I've missed something!)
## Tutorial for using GPT4All-UI
* [Text tutorial, written by **Lucas3DCG**](https://huggingface.co/TheBloke/MPT-7B-Storywriter-GGML/discussions/2#6475d914e9b57ce0caa68888)
* [Video tutorial, by GPT4All-UI's author **ParisNeo**](https://www.youtube.com/watch?v=ds_U0TDzbzI)
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| starcoder.ggmlv3.q4_0.bin | q4_0 | 4 | 10.75 GB | 13.25 GB | Original llama.cpp quant method, 4-bit. |
| starcoder.ggmlv3.q4_1.bin | q4_1 | 4 | 11.92 GB | 14.42 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| starcoder.ggmlv3.q5_0.bin | q5_0 | 5 | 13.09 GB | 15.59 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| starcoder.ggmlv3.q5_1.bin | q5_1 | 5 | 14.26 GB | 16.76 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| starcoder.ggmlv3.q8_0.bin | q8_0 | 8 | 20.11 GB | 22.61 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: Ajan Kanaga, Kalila, Derek Yates, Sean Connelly, Luke, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, trip7s trip, Jonathan Leane, Talal Aujan, Artur Olbinski, Cory Kujawski, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Johann-Peter Hartmann.
Thank you to all my generous patrons and donaters!
# Original model card: Bigcode's Starcoder
# StarCoder
Play with the model on the [StarCoder Playground](https://huggingface.co/spaces/bigcode/bigcode-playground).
## Table of Contents
1. [Model Summary](##model-summary)
2. [Use](##use)
3. [Limitations](##limitations)
4. [Training](##training)
5. [License](##license)
6. [Citation](##citation)
## Model Summary
The StarCoder models are 15.5B parameter models trained on 80+ programming languages from [The Stack (v1.2)](https://huggingface.co/datasets/bigcode/the-stack), with opt-out requests excluded. The model uses [Multi Query Attention](https://arxiv.org/abs/1911.02150), [a context window of 8192 tokens](https://arxiv.org/abs/2205.14135), and was trained using the [Fill-in-the-Middle objective](https://arxiv.org/abs/2207.14255) on 1 trillion tokens.
- **Repository:** [bigcode/Megatron-LM](https://github.com/bigcode-project/Megatron-LM)
- **Project Website:** [bigcode-project.org](https://www.bigcode-project.org)
- **Paper:** [š«StarCoder: May the source be with you!](https://arxiv.org/abs/2305.06161)
- **Point of Contact:** [contact@bigcode-project.org](mailto:contact@bigcode-project.org)
- **Languages:** 80+ Programming languages
## Use
### Intended use
The model was trained on GitHub code. As such it is _not_ an instruction model and commands like "Write a function that computes the square root." do not work well. However, by using the [Tech Assistant prompt](https://huggingface.co/datasets/bigcode/ta-prompt) you can turn it into a capable technical assistant.
**Feel free to share your generations in the Community tab!**
### Generation
```python
# pip install -q transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "bigcode/starcoder"
device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
### Fill-in-the-middle
Fill-in-the-middle uses special tokens to identify the prefix/middle/suffix part of the input and output:
```python
input_text = "