Update config.json

config.json

@@ -2,8 +2,6 @@
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -16,26 +14,12 @@
   "num_hidden_layers": 40,
   "num_key_value_heads": 40,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.38.2",
-  "use_cache": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": true,
   "vocab_size": 32016
 }