measurement.json
Browse files- README.md +65 -0
- measurement.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: teknium/OpenHermes-2.5-Mistral-7B
|
| 3 |
+
tags:
|
| 4 |
+
- mistral
|
| 5 |
+
- instruct
|
| 6 |
+
- finetune
|
| 7 |
+
- chatml
|
| 8 |
+
- gpt4
|
| 9 |
+
- synthetic data
|
| 10 |
+
- distillation
|
| 11 |
+
- dpo
|
| 12 |
+
- rlhf
|
| 13 |
+
- laser
|
| 14 |
+
license: apache-2.0
|
| 15 |
+
language:
|
| 16 |
+
- en
|
| 17 |
+
datasets:
|
| 18 |
+
- mlabonne/chatml_dpo_pairs
|
| 19 |
+
quantized_by: bartowski
|
| 20 |
+
pipeline_tag: text-generation
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
## Exllama v2 Quantizations of NeuralHermes-2.5-Mistral-7B-laser
|
| 24 |
+
|
| 25 |
+
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</a> for quantization.
|
| 26 |
+
|
| 27 |
+
## The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
|
| 28 |
+
|
| 29 |
+
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
|
| 30 |
+
|
| 31 |
+
Conversion was done using the default calibration dataset.
|
| 32 |
+
|
| 33 |
+
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.
|
| 34 |
+
|
| 35 |
+
Original model: https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
## Download instructions
|
| 40 |
+
|
| 41 |
+
With git:
|
| 42 |
+
|
| 43 |
+
```shell
|
| 44 |
+
git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/NeuralHermes-2.5-Mistral-7B-laser-exl2
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
With huggingface hub (credit to TheBloke for instructions):
|
| 48 |
+
|
| 49 |
+
```shell
|
| 50 |
+
pip3 install huggingface-hub
|
| 51 |
+
```
|
| 52 |
+
|
| 53 |
+
To download the `main` (only useful if you only care about measurement.json) branch to a folder called `NeuralHermes-2.5-Mistral-7B-laser-exl2`:
|
| 54 |
+
|
| 55 |
+
```shell
|
| 56 |
+
mkdir NeuralHermes-2.5-Mistral-7B-laser-exl2
|
| 57 |
+
huggingface-cli download bartowski/NeuralHermes-2.5-Mistral-7B-laser-exl2 --local-dir NeuralHermes-2.5-Mistral-7B-laser-exl2 --local-dir-use-symlinks False
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
To download from a different branch, add the `--revision` parameter:
|
| 61 |
+
|
| 62 |
+
```shell
|
| 63 |
+
mkdir NeuralHermes-2.5-Mistral-7B-laser-exl2
|
| 64 |
+
huggingface-cli download bartowski/NeuralHermes-2.5-Mistral-7B-laser-exl2 --revision 4_0 --local-dir NeuralHermes-2.5-Mistral-7B-laser-exl2 --local-dir-use-symlinks False
|
| 65 |
+
```
|
measurement.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|