gurgutan commited on
Commit
9b949f3
1 Parent(s): fceeee4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -2
README.md CHANGED
@@ -7,14 +7,20 @@ tags:
7
  - gpt3
8
  - transformers
9
  ---
 
10
  # ruGPT-13B-4bit
11
  This files are GPTQ model files for sberbank [ruGPT-3.5-13B](https://huggingface.co/ai-forever/ruGPT-3.5-13B) model.
 
12
  ## Technical details
13
- Model was quantized to 4-bit
 
14
  ## Examples of usage
15
- First make sure you have AutoGPTQ installed:
 
16
  GITHUB_ACTIONS=true pip install auto-gptq
 
17
  Then try the following example code:
 
18
  ```python
19
  from transformers import AutoTokenizer, TextGenerationPipeline
20
  from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
 
7
  - gpt3
8
  - transformers
9
  ---
10
+
11
  # ruGPT-13B-4bit
12
  This files are GPTQ model files for sberbank [ruGPT-3.5-13B](https://huggingface.co/ai-forever/ruGPT-3.5-13B) model.
13
+
14
  ## Technical details
15
+ Model was quantized to 4-bit with [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) library
16
+
17
  ## Examples of usage
18
+ First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
19
+
20
  GITHUB_ACTIONS=true pip install auto-gptq
21
+
22
  Then try the following example code:
23
+
24
  ```python
25
  from transformers import AutoTokenizer, TextGenerationPipeline
26
  from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig