Commit
•
aadd35f
1
Parent(s):
7d0fc1f
tagged more
Browse files
README.md
CHANGED
|
@@ -2,9 +2,17 @@
|
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
library_name: transformers
|
| 4 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
-
## NeverSleep's [Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss](https://huggingface.co/NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss)
|
|
|
|
| 8 |
### the other 14 shannons will be remembered. [HQQ quantized](https://mobiusml.github.io/hqq_blog/) to 2 bits with 4 bit attention. Fits on a 3090 with room to grow. Supports full 32k context. I will not combine those assertions.
|
| 9 |
The attention tensors are 4 bit because mixtral reuses it for each expert - so it's only adding 0.4 GB and the quality improve dramatically. See [this](https://huggingface.co/mobiuslabsgmbh/Mixtral-8x7B-v0.1-hf-attn-4bit-moe-2bit-HQQ) but horny and dying of chatml m<|alig>|nant tokenitis.|>
|
| 10 |
|
|
|
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
library_name: transformers
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- HQQ
|
| 7 |
+
- mixtral
|
| 8 |
+
- moe
|
| 9 |
+
- quantized
|
| 10 |
+
- 2bit
|
| 11 |
+
|
| 12 |
---
|
| 13 |
|
| 14 |
+
## NeverSleep's [Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss](https://huggingface.co/NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss) 2 bit HQQ quant.
|
| 15 |
+
## 18.2 GB
|
| 16 |
### the other 14 shannons will be remembered. [HQQ quantized](https://mobiusml.github.io/hqq_blog/) to 2 bits with 4 bit attention. Fits on a 3090 with room to grow. Supports full 32k context. I will not combine those assertions.
|
| 17 |
The attention tensors are 4 bit because mixtral reuses it for each expert - so it's only adding 0.4 GB and the quality improve dramatically. See [this](https://huggingface.co/mobiuslabsgmbh/Mixtral-8x7B-v0.1-hf-attn-4bit-moe-2bit-HQQ) but horny and dying of chatml m<|alig>|nant tokenitis.|>
|
| 18 |
|