Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,4 @@ This is Wizard 8x22, quantized to GPTQ with these parameters:
|
|
| 2 |
|
| 3 |
python3 quant.py alpindale/WizardLM-2-8x22B /workspace/wizard-4bit custom --bits 4 --group_size 128 --desc_act 1 --damp 0.1 --dtype float16 --seqlen 16384 --num_samples 256 --cache_examples 0 --trust_remote_code
|
| 4 |
|
| 5 |
-
The dataset used was openerotica/erotiquant2. I have included a script to
|
|
|
|
| 2 |
|
| 3 |
python3 quant.py alpindale/WizardLM-2-8x22B /workspace/wizard-4bit custom --bits 4 --group_size 128 --desc_act 1 --damp 0.1 --dtype float16 --seqlen 16384 --num_samples 256 --cache_examples 0 --trust_remote_code
|
| 4 |
|
| 5 |
+
The dataset used was openerotica/erotiquant2. I have included a script reconstitute.py to merge the files into one.
|