Hugging Face's logo

TheBloke
/
starcoder-GGML

Text Generation Transformers
starcoder code Eval Results 4 papers
Model card Files Community
2
Edit model card
TheBlokeAI

Bigcode's Starcoder GGML

These files are GGML format model files for Bigcode's 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

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
  • The ctransformers Python library, which includes LangChain support: ctransformers
  • The GPT4All-UI which uses ctransformers: GPT4All-UI
  • rustformers' llm
  • The example starcoder binary provided with 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

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

Thanks, and how to contribute.

Thanks to the 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.

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

banner

Play with the model on the StarCoder Playground.

Table of Contents

  1. Model Summary
  2. Use
  3. Limitations
  4. Training
  5. License
  6. Citation

Model Summary

The StarCoder models are 15.5B parameter models trained on 80+ programming languages from The Stack (v1.2), with opt-out requests excluded. The model uses Multi Query Attention, a context window of 8192 tokens, and was trained using the Fill-in-the-Middle objective on 1 trillion tokens.

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 you can turn it into a capable technical assistant.

Feel free to share your generations in the Community tab!

Generation 

# 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:

input_text = "<fim_prefix>def print_hello_world():\n    <fim_suffix>\n    print('Hello world!')<fim_middle>"
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))

Attribution & Other Requirements

The pretraining dataset of the model was filtered for permissive licenses only. Nevertheless, the model can generate source code verbatim from the dataset. The code's license might require attribution and/or other specific requirements that must be respected. We provide a search index that let's you search through the pretraining data to identify where generated code came from and apply the proper attribution to your code.

Limitations

The model has been trained on source code from 80+ programming languages. The predominant natural language in source code is English although other languages are also present. As such the model is capable of generating code snippets provided some context but the generated code is not guaranteed to work as intended. It can be inefficient, contain bugs or exploits. See the paper for an in-depth discussion of the model limitations.

Training

Model

  • Architecture: GPT-2 model with multi-query attention and Fill-in-the-Middle objective
  • Pretraining steps: 250k
  • Pretraining tokens: 1 trillion
  • Precision: bfloat16

Hardware

  • GPUs: 512 Tesla A100
  • Training time: 24 days

Software

License

The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement here.

Citation 

@article{li2023starcoder,
      title={StarCoder: may the source be with you!}, 
      author={Raymond Li and Loubna Ben Allal and Yangtian Zi and Niklas Muennighoff and Denis Kocetkov and Chenghao Mou and Marc Marone and Christopher Akiki and Jia Li and Jenny Chim and Qian Liu and Evgenii Zheltonozhskii and Terry Yue Zhuo and Thomas Wang and Olivier Dehaene and Mishig Davaadorj and Joel Lamy-Poirier and João Monteiro and Oleh Shliazhko and Nicolas Gontier and Nicholas Meade and Armel Zebaze and Ming-Ho Yee and Logesh Kumar Umapathi and Jian Zhu and Benjamin Lipkin and Muhtasham Oblokulov and Zhiruo Wang and Rudra Murthy and Jason Stillerman and Siva Sankalp Patel and Dmitry Abulkhanov and Marco Zocca and Manan Dey and Zhihan Zhang and Nour Fahmy and Urvashi Bhattacharyya and Wenhao Yu and Swayam Singh and Sasha Luccioni and Paulo Villegas and Maxim Kunakov and Fedor Zhdanov and Manuel Romero and Tony Lee and Nadav Timor and Jennifer Ding and Claire Schlesinger and Hailey Schoelkopf and Jan Ebert and Tri Dao and Mayank Mishra and Alex Gu and Jennifer Robinson and Carolyn Jane Anderson and Brendan Dolan-Gavitt and Danish Contractor and Siva Reddy and Daniel Fried and Dzmitry Bahdanau and Yacine Jernite and Carlos Muñoz Ferrandis and Sean Hughes and Thomas Wolf and Arjun Guha and Leandro von Werra and Harm de Vries},
      year={2023},
      eprint={2305.06161},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
Downloads last month
9
Inference Examples
Text Generation
Inference API (serverless) has been turned off for this model.

Dataset used to train TheBloke/starcoder-GGML

Evaluation results

View on Papers With Code