Commit
·
8825ea3
1
Parent(s):
a54db43
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,43 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: cc-by-nc-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
datasets:
|
3 |
+
- c-s-ale/alpaca-gpt4-data
|
4 |
+
- Open-Orca/OpenOrca
|
5 |
+
- Intel/orca_dpo_pairs
|
6 |
+
- allenai/ultrafeedback_binarized_cleaned
|
7 |
+
- HuggingFaceH4/no_robots
|
8 |
license: cc-by-nc-4.0
|
9 |
+
language:
|
10 |
+
- en
|
11 |
+
library_name: ExLlamaV2
|
12 |
+
pipeline_tag: text-generation
|
13 |
+
tags:
|
14 |
+
- Mistral
|
15 |
+
- SOLAR
|
16 |
+
- Quantized Model
|
17 |
+
- exl2
|
18 |
+
base_model:
|
19 |
+
- rishiraj/meow
|
20 |
---
|
21 |
+
|
22 |
+
# exl2 quants for meow
|
23 |
+
|
24 |
+
This repository includes the quantized models for the [meow](https://huggingface.co/rishiraj/meow) model by [Rishiraj Acharya](https://huggingface.co/rishiraj). meow is a fine-tune of [SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0) with the [no_robots](https://huggingface.co/datasets/HuggingFaceH4/no_robots) dataset.
|
25 |
+
|
26 |
+
## Current models
|
27 |
+
|
28 |
+
| exl2 BPW | Model Branch | Model Size |
|
29 |
+
|-|-|-|
|
30 |
+
| 2-Bit | main | N/A |
|
31 |
+
| 4-Bit | 4bit | N/A |
|
32 |
+
| 5-Bit | 5bit | N/A |
|
33 |
+
| 6-Bit | 6bit | 8.23 GB |
|
34 |
+
| 8-Bit | 8bit | N/A |
|
35 |
+
|
36 |
+
## Where to use
|
37 |
+
|
38 |
+
There are a couple places you can use an exl2 model, here are a few:
|
39 |
+
|
40 |
+
- [oobabooga's Text Gen Webui](https://github.com/oobabooga/text-generation-webui)
|
41 |
+
- [tabbyAPI](https://github.com/theroyallab/tabbyAPI)
|
42 |
+
- [ExUI](https://github.com/turboderp/exui)
|
43 |
+
- [KoboldAI](https://github.com/henk717/KoboldAI)
|