Commit
•
3894956
1
Parent(s):
a415978
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,7 @@ license: apache-2.0
|
|
| 15 |
|
| 16 |
Quantized from fp16.
|
| 17 |
* Weighted quantizations were creating using fp16 GGUF and groups_merged.txt in 105 chunks and n_ctx=512
|
|
|
|
| 18 |
|
| 19 |
For a brief rundown of iMatrix quant performance please see this [PR](https://github.com/ggerganov/llama.cpp/pull/5747)
|
| 20 |
|
|
|
|
| 15 |
|
| 16 |
Quantized from fp16.
|
| 17 |
* Weighted quantizations were creating using fp16 GGUF and groups_merged.txt in 105 chunks and n_ctx=512
|
| 18 |
+
* Static fp16 also included in repo
|
| 19 |
|
| 20 |
For a brief rundown of iMatrix quant performance please see this [PR](https://github.com/ggerganov/llama.cpp/pull/5747)
|
| 21 |
|