NightForger commited on
Commit
afe72b7
·
verified ·
1 Parent(s): 04b00b6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -21,7 +21,7 @@ quantized_by: NightForger
21
  It is just fast gptq 4q version of [this model](https://huggingface.co/IlyaGusev/saiga_nemo_12b).
22
 
23
  # Quantize config:
24
- ```
25
  {
26
  "bits": 4,
27
  "group_size": 128,
@@ -41,7 +41,7 @@ It is just fast gptq 4q version of [this model](https://huggingface.co/IlyaGusev
41
  1024 examples from [SFT set](https://huggingface.co/datasets/IlyaGusev/saiga_scored).
42
 
43
  # Code example (roleplay):
44
- ```
45
  # Please don`t use this code (try vllm or exllama)
46
  import torch
47
  from transformers import AutoTokenizer, AutoConfig, GenerationConfig
 
21
  It is just fast gptq 4q version of [this model](https://huggingface.co/IlyaGusev/saiga_nemo_12b).
22
 
23
  # Quantize config:
24
+ ```json
25
  {
26
  "bits": 4,
27
  "group_size": 128,
 
41
  1024 examples from [SFT set](https://huggingface.co/datasets/IlyaGusev/saiga_scored).
42
 
43
  # Code example (roleplay):
44
+ ```python
45
  # Please don`t use this code (try vllm or exllama)
46
  import torch
47
  from transformers import AutoTokenizer, AutoConfig, GenerationConfig