Update config.json

config.json

@@ -20,32 +20,14 @@
   "hidden_size": 4544,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "max_position_embeddings": 2048,
   "model_type": "falcon",
   "multi_query": true,
   "new_decoder_architecture": false,
   "num_attention_heads": 71,
   "num_hidden_layers": 32,
-  "num_kv_heads": 71,
   "parallel_attn": true,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float32",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
-    "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"
-  },
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "torch_dtype": "float16",
-  "transformers_version": "4.38.2",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.27.4",
   "use_cache": true,
   "vocab_size": 65024
 }