Update README.md
Browse files
README.md
CHANGED
|
@@ -35,6 +35,7 @@ The quantization method included *32-bit* quantization of the following Layers:
|
|
| 35 |
- o_proj
|
| 36 |
- down_proj
|
| 37 |
- lm_head
|
|
|
|
| 38 |
Rest of the remaining layers were quantized to *q3_k_l*
|
| 39 |
|
| 40 |
---
|
|
|
|
| 35 |
- o_proj
|
| 36 |
- down_proj
|
| 37 |
- lm_head
|
| 38 |
+
|
| 39 |
Rest of the remaining layers were quantized to *q3_k_l*
|
| 40 |
|
| 41 |
---
|