LoupGarou's Starcoderplus Guanaco GPT4 15B V1.0 GGML
These files are StarCoder GGML format model files for LoupGarou's Starcoderplus Guanaco GPT4 15B V1.0.
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 that work with this GGML model.
These files were quantised using hardware kindly provided by Latitude.sh.
Repositories available
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- 2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference
- Unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: Guanaco
### Human: {prompt}
### Assistant:
Compatibilty
These files are not compatible with llama.cpp or text-generation-webui.
They can be used with:
- KoboldCpp, a powerful inference engine based on llama.cpp with full GPU acceleration and good UI.
- LM Studio, a fully featured local GUI for GGML inference on Windows and macOS.
- LoLLMs-WebUI a web UI which supports nearly every backend out there. Use ctransformers backend for support for this model.
- ctransformers: for use in Python code, including LangChain support.
- rustformers' llm
- The example
starcoderbinary 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 LoLLMs-WebUI:
Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|---|---|---|---|---|---|
| starcoderplus-guanaco-gpt4.ggmlv1.q4_0.bin | q4_0 | 4 | 10.75 GB | 13.25 GB | 4-bit. |
| starcoderplus-guanaco-gpt4.ggmlv1.q4_1.bin | q4_1 | 4 | 11.92 GB | 14.42 GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| starcoderplus-guanaco-gpt4.ggmlv1.q5_0.bin | q5_0 | 5 | 13.09 GB | 15.59 GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
| starcoderplus-guanaco-gpt4.ggmlv1.q5_1.bin | q5_1 | 5 | 14.26 GB | 16.76 GB | 5-bit. Even higher accuracy, resource usage and slower inference. |
| starcoderplus-guanaco-gpt4.ggmlv1.q8_0.bin | q8_0 | 8 | 20.11 GB | 22.61 GB | 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
Discord
For further support, and discussions on these models and AI in general, join us at:
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.
- Patreon: https://patreon.com/TheBlokeAI
- Ko-Fi: https://ko-fi.com/TheBlokeAI
Special thanks to: Luke from CarbonQuill, Aemon Algiz.
Patreon special mentions: Space Cruiser, Nikolai Manek, Sam, Chris McCloskey, Rishabh Srivastava, Kalila, Spiking Neurons AB, Khalefa Al-Ahmad, WelcomeToTheClub, Chadd, Lone Striker, Viktor Bowallius, Edmond Seymore, Ai Maven, Chris Smitley, Dave, Alexandros Triantafyllidis, Luke @flexchar, Elle, ya boyyy, Talal Aujan, Alex , Jonathan Leane, Deep Realms, Randy H, subjectnull, Preetika Verma, Joseph William Delisle, Michael Levine, chris gileta, K, Oscar Rangel, LangChain4j, Trenton Dambrowitz, Eugene Pentland, Johann-Peter Hartmann, Femi Adebogun, Illia Dulskyi, senxiiz, Daniel P. Andersen, Sean Connelly, Artur Olbinski, RoA, Mano Prime, Derek Yates, Raven Klaugh, David Flickinger, Willem Michiel, Pieter, Willian Hasse, vamX, Luke Pendergrass, webtim, Ghost , Rainer Wilmers, Nathan LeClaire, Will Dee, Cory Kujawski, John Detwiler, Fred von Graf, biorpg, Iucharbius , Imad Khwaja, Pierre Kircher, terasurfer , Asp the Wyvern, John Villwock, theTransient, zynix , Gabriel Tamborski, Fen Risland, Gabriel Puliatti, Matthew Berman, Pyrater, SuperWojo, Stephen Murray, Karl Bernard, Ajan Kanaga, Greatston Gnanesh, Junyu Yang.
Thank you to all my generous patrons and donaters!
Original model card: LoupGarou's Starcoderplus Guanaco GPT4 15B V1.0
Starcoderplus-Guanaco-GPT4-15B-V1.0 Model Card
Starcoderplus-Guanaco-GPT4-15B-V1.0 is a language model that combines the strengths of the Starcoderplus base model, an expansion of the orginal openassistant-guanaco dataset re-imagined using 100% GPT-4 answers, and additional data on abstract algebra and physics for finetuning. The original openassistant-guanaco dataset questions were trimmed to within 2 standard deviations of token size for input and output pairs and all non-english data was been removed to reduce training size requirements.
Model Description
This model is built on top of the Starcoderplus base model, a large language model which is a fine-tuned version of StarCoderBase. The Starcoderplus base model was further finetuned using QLORA on the revised openassistant-guanaco dataset questions that were 100% re-imagined using GPT-4.
Intended Use
This model is designed to be used for a wide array of text generation tasks that require understanding and generating English text. The model is expected to perform well in tasks such as answering questions, writing essays, summarizing text, translation, and more. However, given the specific data processing and finetuning done, it might be particularly effective for tasks related to English language question-answering systems.
Limitations
Despite the powerful capabilities of this model, users should be aware of its limitations. The model's knowledge is up to date only until the time it was trained, and it doesn't know about events in the world after that. It can sometimes produce incorrect or nonsensical responses, as it doesn't understand the text in the same way humans do. It should be used as a tool to assist in generating text and not as a sole source of truth.
How to use
Here is an example of how to use this model:
from transformers import AutoModelForCausalLM, AutoTokenizer
import time
import torch
class Chatbot:
def __init__(self, model_name):
self.tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side='left')
self.model = AutoModelForCausalLM.from_pretrained(model_name, load_in_4bit=True, torch_dtype=torch.bfloat16)
if self.tokenizer.pad_token_id is None:
self.tokenizer.pad_token_id = self.tokenizer.eos_token_id
def get_response(self, prompt):
inputs = self.tokenizer.encode_plus(prompt, return_tensors="pt", padding='max_length', max_length=100)
if next(self.model.parameters()).is_cuda:
inputs = {name: tensor.to('cuda') for name, tensor in inputs.items()}
start_time = time.time()
tokens = self.model.generate(input_ids=inputs['input_ids'],
attention_mask=inputs['attention_mask'],
pad_token_id=self.tokenizer.pad_token_id,
max_new_tokens=400)
end_time = time.time()
output_tokens = tokens[0][inputs['input_ids'].shape[-1]:]
output = self.tokenizer.decode(output_tokens, skip_special_tokens=True)
time_taken = end_time - start_time
return output, time_taken
def main():
chatbot = Chatbot("LoupGarou/Starcoderplus-Guanaco-GPT4-15B-V1.0")
while True:
user_input = input("Enter your prompt: ")
if user_input.lower() == 'quit':
break
output, time_taken = chatbot.get_response(user_input)
print("\033[33m" + output + "\033[0m")
print("Time taken to process: ", time_taken, "seconds")
print("Exited the program.")
if __name__ == "__main__":
main()
Training Procedure
The base Starcoderplus model was finetuned on the modified openassistant-guanaco dataset 100% re-imagined with GPT4 answers using QLORA. All non-English data was also removed from this finetuning dataset to reduce trainign size and time.
Acknowledgements
This model, Starcoderplus-Guanaco-GPT4-15B-V1.0, builds upon the strengths of the Starcoderplus and the openassistant-guanaco dataset.
A sincere appreciation goes out to the developers and the community involved in the creation and refinement of these models. Their commitment to providing open source tools and datasets have been instrumental in making this project a reality.
Moreover, a special note of thanks to the Hugging Face team, whose transformative library has not only streamlined the process of model creation and adaptation, but also democratized the access to state-of-the-art machine learning technologies. Their impact on the development of this project cannot be overstated.