smpanaro commited on
Commit
87a85b6
1 Parent(s): e059b48

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -0
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ datasets:
4
+ - wikitext
5
+ ---
6
+
7
+ [gpt2](https://huggingface.co/openai-community/gpt2) quantized to 4-bit using [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ).
8
+
9
+ To use:
10
+
11
+ ```shell
12
+ pip install auto-gptq
13
+ ```
14
+
15
+ ```python
16
+ from transformers import AutoModelForCausalLM, AutoTokenizer
17
+ from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
18
+
19
+ model_name = "smpanaro/gpt2-AutoGPTQ-4bit-128g"
20
+ model = AutoGPTQForCausalLM.from_quantized(model_name)
21
+ ```