# Nick Roshdieh's Evol Replit v1 GGML
These files are Replit GGML format model files for [Nick Roshdieh's Evol Replit v1](https://huggingface.co/nickrosh/Evol-Replit-v1).
Please note that these GGMLs are **not compatible with llama.cpp, text-generation-webui or llama-cpp-python**. 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](https://www.latitude.sh/accelerate).
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Evol-Replit-v1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Evol-Replit-v1-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/nickrosh/Evol-Replit-v1)
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction: {prompt}
### Response:
```
## Compatibilty
These files are **not** compatible with llama.cpp, text-generation-webui or llama-cpp-python.
They can be used with:
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a powerful inference engine based on llama.cpp with full GPU acceleration and good UI.
* [LM Studio](https://lmstudio.ai/), a fully featured local GUI for GGML inference on Windows and macOS.
* [LoLLMs-WebUI](https://github.com/ParisNeo/LoLLMs-WebUI) a web UI which supports nearly every backend out there. Use ctransformers backend for support for this model.
* [ctransformers](https://github.com/marella/ctransformers): for use in Python code, including LangChain support.
* [rustformers' llm](https://github.com/rustformers/llm)
* The example `replit` 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 LoLLMs-WebUI:
* [Video tutorial, by LoLLMs-WebUI's author **ParisNeo**](https://youtu.be/vBU1b5n0GMU)
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| evol-replit-v1.ggmlv1.q4_0.bin | q4_0 | 4 | 1.46 GB| 3.96 GB | 4-bit. |
| evol-replit-v1.ggmlv1.q4_1.bin | q4_1 | 4 | 1.63 GB| 4.13 GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| evol-replit-v1.ggmlv1.q5_0.bin | q5_0 | 5 | 1.79 GB| 4.29 GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
| evol-replit-v1.ggmlv1.q5_1.bin | q5_1 | 5 | 1.95 GB| 4.45 GB | 5-bit. Even higher accuracy, resource usage and slower inference. |
| evol-replit-v1.ggmlv1.q8_0.bin | q8_0 | 8 | 2.76 GB| 5.26 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:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## 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.
**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: Nick Roshdieh's Evol Replit v1
This model uses the Evol-Instruct-Code-80k-v1 dataset generated using the [Evol-Teacher](https://github.com/nickrosh/evol-teacher) repo. Currently, WizardCoder is one the most performant Code Generation models, being beaten only by ChatGPT. This takes the Code Alpaca 20k dataset and evolves each instruction through a randomly chosen evolution prompt to increase instruction complexity. These prompts range from increase time/space complexity, to increasing requirements, to adding erroneus code to improve robustness, etc. This is done three times with pruning and post processing to remove unwanted instructions and responses. The iterative addition of more complexity gives higher quality and more in-depth instructions than what is ususally generated in Alpaca methods. This, like in the case of WizardCoder and WizardLM, can lead to strong performance that gets very close to RLHF model performance.
This model uses [ReplitLM](https://huggingface.co/replit/replit-code-v1-3b) fine tuned with the following parameters:
```bash
--model_name_or_path replit/replit-code-v1-3b \
--data_path ./data/EvolInstruct-Code-80k/EvolInstruct-Code-80k.json \
--output_dir ./checkpoints \
--num_train_epochs 3 \
--per_device_train_batch_size 1 \
--gradient_accumulation_steps 8 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 50 \
--save_total_limit 2 \
--learning_rate 2e-5 \
--weight_decay 0. \
--warmup_ratio 0.03 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--model_max_length 2000 \
--bf16 True \
--tf32 True
```
