juanako-7b-UNA-exl2 / README.md
bartowski's picture
Add 4.0 link
81389b9
---
license: apache-2.0
tags:
- alignment-handbook
- generated_from_trainer
- juanako
- mistral
- UNA
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: juanako-7b-UNA
results:
- task:
type: text-generation
name: TruthfulQA (MC2)
dataset:
type: text-generation
name: truthful_qa
config: multiple_choice
split: validation
metrics:
- type: accuracy
value: 65.13
verified: true
- task:
type: text-generation
name: ARC-Challenge
dataset:
type: text-generation
name: ai2_arc
config: ARC-Challenge
split: test
metrics:
- type: accuracy
value: 68.17
verified: true
- task:
type: text-generation
name: HellaSwag
dataset:
type: text-generation
name: Rowan/hellaswag
split: test
metrics:
- type: accuracy
value: 85.34
verified: true
- task:
type: text-generation
name: Winogrande
dataset:
type: text-generation
name: winogrande
config: winogrande_debiased
split: test
metrics:
- type: accuracy
value: 78.85
verified: true
- task:
type: text-generation
name: MMLU
dataset:
type: text-generation
name: cais/mmlu
config: all
split: test
metrics:
- type: accuracy
value: 62.47
verified: true
- task:
type: text-generation
name: PiQA
dataset:
type: text-generation
name: piqa
split: test
metrics:
- type: accuracy
value: 83.57
- task:
type: text-generation
name: DROP
dataset:
type: text-generation
name: drop
split: validation
metrics:
- type: accuracy
value: 38.74
verified: true
- task:
type: text-generation
name: PubMedQA
dataset:
type: text-generation
name: bigbio/pubmed_qa
config: pubmed_qa_artificial_bigbio_qa
split: validation
metrics:
- type: accuracy
value: 76.0
quantized_by: bartowski
pipeline_tag: text-generation
---
## Exllama v2 Quantizations of juanako-7b-UNA
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.10">turboderp's ExLlamaV2 v0.0.10</a> for quantization.
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Conversion was done using wikitext-103-raw-v1-test.parquet as calibration dataset.
Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
Original model: https://huggingface.co/fblgit/juanako-7b-UNA
<a href="https://huggingface.co/bartowski/juanako-7b-UNA-exl2/tree/4_0">4.0 bits per weight</a>
<a href="https://huggingface.co/bartowski/juanako-7b-UNA-exl2/tree/5_0">5.0 bits per weight</a>
<a href="https://huggingface.co/bartowski/juanako-7b-UNA-exl2/tree/6_0">6.0 bits per weight</a>
<a href="https://huggingface.co/bartowski/juanako-7b-UNA-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/bartowski/juanako-7b-UNA-exl2
```
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 `juanako-7b-UNA-exl2`:
```shell
mkdir juanako-7b-UNA-exl2
huggingface-cli download bartowski/juanako-7b-UNA-exl2 --local-dir juanako-7b-UNA-exl2 --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir juanako-7b-UNA-exl2
huggingface-cli download bartowski/juanako-7b-UNA-exl2 --revision 4_0 --local-dir juanako-7b-UNA-exl2 --local-dir-use-symlinks False
```