---
license: apache-2.0
library_name: transformers
tags:
- not-for-all-audiences
- chemistry
- math
- code
- physics
datasets:
- Locutusque/hercules-v2.0
widget:
- example_title: "Derivative"
text: "<|im_start|>user\nIn this task, you are given a description of an object and its surroundings. Your task is to describe the motion of the object mentioned in the description using differential equations. The answer should be a mathematical expression in t. Description: A ball is thrown up at 30 ft/sec from 3 feet off the ground. Solve this step-by-step, explaining each step in detail.<|im_end|>\n<|im_start|>assistant\n"
output:
text: "Let h(t) be the height of the ball at time t after it was thrown. We know that when the ball is thrown, it has an initial velocity v0 = 30 ft/sec and initial height y0 = 3 ft. We also know that the acceleration due to gravity g = -32 ft/sec^2.\n\nTo solve for the motion of the ball, we can use the equation for vertical motion with acceleration due to gravity:\n\nh(t) = v0 * t + (1/2) * g * t^2 + y0\n\nSubstituting the values given in the problem, we get:\n\ny(t) = (30)(t) + (1/2)(-32)(t)^2 + 3\n\nNow, let's simplify the equation:\n\ny(t) = 30t - 16t^2 + 3\n\nThis is the final solution for the height of the ball as a function of time."
quantized_by: bartowski
pipeline_tag: text-generation
---
## Exllama v2 Quantizations of Hercules-2.0-Mistral-7B
Using turboderp's ExLlamaV2 v0.0.13 for quantization.
The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Original model: https://huggingface.co/Locutusque/Hercules-2.0-Mistral-7B
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/bartowski/Hercules-2.0-Mistral-7B-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/bartowski/Hercules-2.0-Mistral-7B-exl2/tree/6_5) | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
| [5_0](https://huggingface.co/bartowski/Hercules-2.0-Mistral-7B-exl2/tree/5_0) | 5.0 | 6.0 | 6.0 GB | 7.4 GB | 9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
| [4_25](https://huggingface.co/bartowski/Hercules-2.0-Mistral-7B-exl2/tree/4_25) | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| [3_5](https://huggingface.co/bartowski/Hercules-2.0-Mistral-7B-exl2/tree/3_5) | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. |
## Download instructions
With git:
```shell
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Hercules-2.0-Mistral-7B-exl2 Hercules-2.0-Mistral-7B-exl2-6_5
```
With huggingface hub (credit to TheBloke for instructions):
```shell
pip3 install huggingface-hub
```
To download the `main` (only useful if you only care about measurement.json) branch to a folder called `Hercules-2.0-Mistral-7B-exl2`:
```shell
mkdir Hercules-2.0-Mistral-7B-exl2
huggingface-cli download bartowski/Hercules-2.0-Mistral-7B-exl2 --local-dir Hercules-2.0-Mistral-7B-exl2 --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
Linux:
```shell
mkdir Hercules-2.0-Mistral-7B-exl2-6_5
huggingface-cli download bartowski/Hercules-2.0-Mistral-7B-exl2 --revision 6_5 --local-dir Hercules-2.0-Mistral-7B-exl2-6_5 --local-dir-use-symlinks False
```
Windows (which apparently doesn't like _ in folders sometimes?):
```shell
mkdir Hercules-2.0-Mistral-7B-exl2-6.5
huggingface-cli download bartowski/Hercules-2.0-Mistral-7B-exl2 --revision 6_5 --local-dir Hercules-2.0-Mistral-7B-exl2-6.5 --local-dir-use-symlinks False
```
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski