Update README.md

README.md

@@ -30,15 +30,15 @@ effi 7b GPTQ is a quantized version of effi 7b whiich is a 7 billion parameter m
 
 ### Qunatization Configuration
 
- - bits: 4,
- - damp_percent: 0.1,
- - dataset: "wikitext2",
- - desc_act: false,
- - group_size: 128,
- - modules_in_block_to_quantize: null,
- - quant_method: "gptq",
- - sym: true,
- - true_sequential: true
+ - **bits:** 4,
+ - **damp_percent** 0.1,
+ - **dataset:** "wikitext2",
+ - **desc_act:** false,
+ - **group_size:** 128,
+ - **modules_in_block_to_quantize:** null,
+ - **quant_method:** "gptq",
+ - **sym:** true,
+ - **true_sequential:** true
 
 ### Example of usage
 
@@ -79,9 +79,9 @@ print(f"{tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tok
 ```
 
 ### Framework versions
-- Transformers 4.37.2
-- optimum 1.16.2
-- auto-gptq 0.6.0
+- **Transformers** 4.37.2
+- **optimum** 1.16.2
+- **auto-gptq** 0.6.0
 
 ### Citation