Hugging Face's logo

bgsach
/
WizardCoder-Python-13B-V1.0-ct2-float16

Transformers
code
Model card Files
xet
 Community
bgsach commited on
Commit
9333ab2
·
1 Parent(s): 0ad37c0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -14,6 +14,6 @@ been negatively affected by the quantization process.
14
 
15
  The command run to quantize the model was:
16
 
17
- `ct2-transformers-converter --model ./models-hf/WizardLM/WizardCoder-Python-13B-V1.0 --quantization int8_float16 --output_dir ./models-ct/WizardLM/WizardCoder-Python-13B-V1.0-ct2-int8_float16`
18
 
19
  The quantization was run on a 'high-mem', CPU only (8 core, 51GB) colab instance and took approximately 10 minutes.
 
14
 
15
  The command run to quantize the model was:
16
 
17
+ `ct2-transformers-converter --model ./models-hf/WizardLM/WizardCoder-Python-13B-V1.0 --quantization float16 --output_dir ./models-ct/WizardLM/WizardCoder-Python-13B-V1.0-ct2-float16`
18
 
19
  The quantization was run on a 'high-mem', CPU only (8 core, 51GB) colab instance and took approximately 10 minutes.