Commit
•
847edef
1
Parent(s):
6826888
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ inference: false
|
|
| 4 |
---
|
| 5 |
4-bit quantization of the vicuna-13b-v1.1 model.
|
| 6 |
|
| 7 |
-
The delta was added to the original LLaMa weights using FastChat.
|
| 8 |
Quantization and inference with GPTQ-For-LLaMa (commit 58c8ab4).
|
| 9 |
|
| 10 |
Quantization args: $MODEL_DIRECTORY, c4, wbits 4, true-sequential, act-order, groupsize 128. \
|
|
|
|
| 4 |
---
|
| 5 |
4-bit quantization of the vicuna-13b-v1.1 model.
|
| 6 |
|
| 7 |
+
The delta was added to the original LLaMa weights using FastChat. \
|
| 8 |
Quantization and inference with GPTQ-For-LLaMa (commit 58c8ab4).
|
| 9 |
|
| 10 |
Quantization args: $MODEL_DIRECTORY, c4, wbits 4, true-sequential, act-order, groupsize 128. \
|