MLDataScientist
/

Mistral-Large-Instruct-2407-GPTQ-3bit

Text Generation

Model card Files Files and versions Community

MLDataScientist commited on Jan 16

Commit

17613f1

·

verified ·

1 Parent(s): 1d7f12b

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -9,7 +9,7 @@ tags:
 This is a 3bit AutoRound GPTQ version of Mistral-Large-Instruct-2407.
 This conversion used model-*.safetensors.
-Quantization script (it takes around 520 GB RAM and A40 GPU 40GB around 20 hours to convert):
 ```
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch

 This is a 3bit AutoRound GPTQ version of Mistral-Large-Instruct-2407.
 This conversion used model-*.safetensors.
+Quantization script (it takes around 520 GB RAM and A40 GPU 48GB around 20 hours to convert):
 ```
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch