Update README.md

README.md

@@ -10,28 +10,17 @@ Link: [https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct](https://hu
 ## Quantization Configurations
 ```
 "quantization_config": {
-    "batch_size": 1,
     "bits": 4,
-    "block_name_to_quantize": null,
-    "cache_block_outputs": true,
-    "damp_percent": 0.1,
-    "dataset": null,
-    "desc_act": false,
-    "exllama_config": {
-      "version": 1
-    },
+    "checkpoint_format": "gptq",
+    "damp_percent": 0.01,
+    "desc_act": true,
     "group_size": 128,
-    "max_input_length": null,
-    "model_seqlen": null,
-    "module_name_preceding_first_block": null,
-    "modules_in_block_to_quantize": null,
-    "pad_token_id": null,
+    "model_file_base_name": null,
+    "model_name_or_path": null,
     "quant_method": "gptq",
+    "static_groups": false,
     "sym": true,
-    "tokenizer": null,
-    "true_sequential": true,
-    "use_cuda_fp16": false,
-    "use_exllama": true
+    "true_sequential": true
   },
 ```