# Wizard Mega 13B GGML
This is GGML format quantised 4bit and 5bit models of [OpenAccess AI Collective's Wizard Mega 13B](https://huggingface.co/openaccess-ai-collective/wizard-mega-13b).
This repo is the result of quantising to 4bit and 5bit GGML for CPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp).
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/wizard-mega-13B-GPTQ).
* [4-bit, 5-bit 8-bit GGML models for llama.cpp CPU (+CUDA) inference](https://huggingface.co/TheBloke/wizard-mega-13B-GGML).
* [OpenAccess AI Collective's original float16 HF format repo for GPU inference and further conversions](https://huggingface.co/openaccess-ai-collective/wizard-mega-13b).
## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
I have quantised the GGML files in this repo with the latest version. Therefore you will require llama.cpp compiled on May 19th or later (commit `2d5db48` or later) to use them.
For files compatible with the previous version of llama.cpp, please see branch `previous_llama_ggmlv2`.
## Provided files
| Name | Quant method | Bits | Size | RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
`wizard-mega-13B.ggmlv3.q4_0.bin` | q4_0 | 4bit | 8.14GB | 10.5GB | 4-bit. |
`wizard-mega-13B.ggmlv3.q4_1.bin` | q5_0 | 5bit | 8.95GB | 11.0GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.|
`wizard-mega-13B.ggmlv3.q5_0.bin` | q5_0 | 5bit | 8.95GB | 11.0GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
`wizard-mega-13B.ggmlv3.q5_1.bin` | q5_1 | 5bit | 9.76GB | 12.25GB | 5-bit. Even higher accuracy, and higher resource usage and slower inference. |
`wizard-mega-13B.ggmlv3.q8_0.bin` | q8_0 | 8bit | 14.6GB | 17GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 8 -m wizard-mega-13B.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: write a story about llamas ### Response:"
```
Change `-t 8` to the number of physical CPU cores you have.
## How to run in `text-generation-webui`
GGML models can be loaded into text-generation-webui by installing the llama.cpp module, then placing the ggml model file in a model folder as usual.
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
Note: at this time text-generation-webui may not support the new May 19th llama.cpp quantisation methods for q4_0, q4_1 and q8_0 files.
## 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
**Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
Thank you to all my generous patrons and donaters!
# Original Wizard Mega 13B model card
Wizard Mega is a Llama 13B model fine-tuned on the [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered), [WizardLM](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered), and [Wizard-Vicuna](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered) datasets. These particular datasets have all been filtered to remove responses where the model responds with "As an AI language model...", etc or when the model refuses to respond.
## Release (Epoch Two)
The Wizard Mega 13B SFT model is being released after two epochs as the eval loss increased during the 3rd (final planned epoch). Because of this, we have preliminarily decided to use the epoch 2 checkpoint as the final release candidate. https://wandb.ai/wing-lian/vicuna-13b/runs/5uebgm49
## Build
Wizard Mega was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 8xA100 80GB for 15 hours. The configuration to duplicate this build is provided in this repo's [/config folder](https://huggingface.co/openaccess-ai-collective/wizard-mega-13b/tree/main/configs).
## Examples
````
### Instruction: write Python code that returns the first n numbers of the Fibonacci sequence using memoization.
### Assistant:
```python
def fib(n):
if n < 2:
return n
elif n in cache:
return cache[n]
else:
a, b = 0, 1
for i in range(2, n+1):
cache[i] = a
a, b = b, a + b
return cache[n]
def first_n(n):
fib_list = [fib(i) for i in range(n+1)]
return fib_list[:n]
```
This function uses memoization to store the values of previous Fibonacci numbers in a cache. This way, if the same number is requested again, it can be returned immediately without recalculating it.
The `first_n` function takes an integer `n` as input, and calculates the first n numbers of the Fibonacci sequence using memoization. It returns a list of those numbers.
````
```
### Instruction: Finish the joke, a mechanic and a car salesman walk into a bar...
### Assistant: ...and the bartender says "Hey guys, what can I get for you?" The mechanic replies, "I'll have a beer, but make it a quick one. I have to fix this guy's car before he finds out I
fiddled with his brakes." The salesman quips, "And I'll have a martini, shaken not stirred. After all, I have to sell this guy a car that doesn't break down on him within the first year of ownership."
```
