Update README.md
Browse files
README.md
CHANGED
@@ -5,4 +5,13 @@ Big thank you to TheBloke for uploading the HF version above. Unfortunately, hi
|
|
5 |
GPTQ quantization using https://github.com/0cc4m/GPTQ-for-LLaMa for compatibility with 0cc4m's fork of KoboldAI.
|
6 |
|
7 |
Command used to quantize:
|
8 |
-
```python llama.py c:\stable-vicuna-13B-HF c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors 4bit-128g.safetensors```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
GPTQ quantization using https://github.com/0cc4m/GPTQ-for-LLaMa for compatibility with 0cc4m's fork of KoboldAI.
|
6 |
|
7 |
Command used to quantize:
|
8 |
+
```python llama.py c:\stable-vicuna-13B-HF c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors 4bit-128g.safetensors```
|
9 |
+
|
10 |
+
This model works best with the following prompting. Also, it really does not like to stop on its own and will likely keep going on forever if you let it.
|
11 |
+
|
12 |
+
```### Human:
|
13 |
+
What is 2+2?
|
14 |
+
|
15 |
+
### Assistant:
|
16 |
+
|
17 |
+
```
|