Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,40 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: other
|
| 3 |
-
license_name: tongyi-qianwen
|
| 4 |
-
license_link: LICENSE
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: tongyi-qianwen
|
| 4 |
+
license_link: LICENSE
|
| 5 |
+
tags:
|
| 6 |
+
- chat
|
| 7 |
+
- qwen
|
| 8 |
+
- opus
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
```
|
| 12 |
+
e88 88e d8
|
| 13 |
+
d888 888b 8888 8888 ,"Y88b 888 8e d88
|
| 14 |
+
C8888 8888D 8888 8888 "8" 888 888 88b d88888
|
| 15 |
+
Y888 888P Y888 888P ,ee 888 888 888 888
|
| 16 |
+
"88 88" "88 88" "88 888 888 888 888
|
| 17 |
+
b
|
| 18 |
+
8b,
|
| 19 |
+
|
| 20 |
+
e88'Y88 d8 888
|
| 21 |
+
d888 'Y ,"Y88b 888,8, d88 ,e e, 888
|
| 22 |
+
C8888 "8" 888 888 " d88888 d88 88b 888
|
| 23 |
+
Y888 ,d ,ee 888 888 888 888 , 888
|
| 24 |
+
"88,d88 "88 888 888 888 "YeeP" 888
|
| 25 |
+
|
| 26 |
+
PROUDLY PRESENTS
|
| 27 |
+
```
|
| 28 |
+
|
| 29 |
+
## magnum-72b-v1-iMat-GGUF
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
Quantized from fp16 with love.
|
| 34 |
+
* Weighted quantizations were created using fp16 GGUF and [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) in 92 chunks and n_ctx=512
|
| 35 |
+
|
| 36 |
+
For a brief rundown of iMatrix quant performance please see this [PR](https://github.com/ggerganov/llama.cpp/pull/5747)
|
| 37 |
+
|
| 38 |
+
<b>All quants are verified working prior to uploading to repo for your safety and convenience. </b>
|
| 39 |
+
|
| 40 |
+
Original model card [here](https://huggingface.co/alpindale/magnum-72b-v1)
|