---
license: other
tags:
- axolotl
- generated_from_trainer
- Mistral
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- science
- physics
- chemistry
- biology
- math
base_model: alpindale/Mistral-7B-v0.2-hf
datasets:
- allenai/ai2_arc
- camel-ai/physics
- camel-ai/chemistry
- camel-ai/biology
- camel-ai/math
- metaeval/reclor
- openbookqa
- mandyyyyii/scibench
- derek-thomas/ScienceQA
- TIGER-Lab/ScienceEval
- jondurbin/airoboros-3.2
- LDJnr/Capybara
- Cot-Alpaca-GPT4-From-OpenHermes-2.5
- STEM-AI-mtl/Electrical-engineering
- knowrohit07/saraswati-stem
- sablo/oasst2_curated
- lmsys/lmsys-chat-1m
- TIGER-Lab/MathInstruct
- bigbio/med_qa
- meta-math/MetaMathQA-40K
- openbookqa
- piqa
- metaeval/reclor
- derek-thomas/ScienceQA
- scibench
- sciq
- Open-Orca/SlimOrca
- migtissera/Synthia-v1.3
- TIGER-Lab/ScienceEval
- allenai/WildChat
- microsoft/orca-math-word-problems-200k
- openchat/openchat_sharegpt4_dataset
- teknium/GPTeacher-General-Instruct
- m-a-p/CodeFeedback-Filtered-Instruction
quantized_by: suparious
pipeline_tag: text-generation
---
## Exllama v2 Quantizations of Weyaxi/Einstein-v5-v0.2-7B

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.16">turboderp's ExLlamaV2 v0.0.16</a> for quantization.

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Original model: Weyaxi/Einstein-v5-v0.2-7B

Model Size: 7b

| Branch | Bits | lm_head bits | Dataset | Size | Description |
| ----- | ---- | ------- | ------- | ------- | ------------ |
| [8_0](https://huggingface.co/suparious/Einstein-v5-v0.2-7B-exl2/tree/8_0) | 8.0 | 8.0 | Default | 9.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/suparious/Einstein-v5-v0.2-7B-exl2/tree/6_5) | 6.5 | 8.0 | Default | 8.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
| [5_0](https://huggingface.co/suparious/Einstein-v5-v0.2-7B-exl2/tree/5_0) | 5.0 | 6.0 | Default | 7.4 GB | Slightly lower perplexity vs 6.5. |
| [4_0](https://huggingface.co/suparious/Einstein-v5-v0.2-7B-exl2/tree/4_0) | 4.0 | 6.0 | Default | 6.5 GB | Just under GPTQ equivalent bits per weight. |

All VRAM requirements estimated from 16k context. For 32k context add ~2 GB.
 
<a href="https://huggingface.co/suparious/Einstein-v5-v0.2-7B-exl2/tree/4_0">4.0 bits per weight</a>
 
<a href="https://huggingface.co/suparious/Einstein-v5-v0.2-7B-exl2/tree/5_0">5.0 bits per weight</a>
 
<a href="https://huggingface.co/suparious/Einstein-v5-v0.2-7B-exl2/tree/6_5">6.5 bits per weight</a>
 
<a href="https://huggingface.co/suparious/Einstein-v5-v0.2-7B-exl2/tree/8_0">8.0 bits per weight</a>

## Download instructions

With git:

```shell
git clone --single-branch --branch 4_0 https://huggingface.co/suparious/Einstein-v5-v0.2-7B-exl2
```

With huggingface hub (credit to TheBloke and bartowski 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 `Einstein-v5-v0.2-7B-exl2`:

```shell
mkdir Einstein-v5-v0.2-7B-exl2
huggingface-cli download suparious/Einstein-v5-v0.2-7B-exl2 --local-dir Einstein-v5-v0.2-7B-exl2 --local-dir-use-symlinks False
```

To download from a different branch, add the `--revision` parameter:

```shell
mkdir Einstein-v5-v0.2-7B-exl2-6_5
huggingface-cli download suparious/Einstein-v5-v0.2-7B-exl2 --revision 6_5 --local-dir Einstein-v5-v0.2-7B-exl2-6_5 --local-dir-use-symlinks False
```