Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,9 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen2-7B-Instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
These are a whole bunch of conversions of qwen7b v2 in an attempt to fix the reduced performance while quantizing.
|
| 7 |
+
The bf16 versions will NOT work with apple GPUs but will works with most cpus and newer nvidia cards ( older ones like 1080 series don't support bf16 inference well).
|
| 8 |
+
|
| 9 |
+
Perplexity benchmarks will come later once an automated suite is written by me or whoemever, sorry have just been too busy and doing those properly takes all day.
|