Upload config

config.json

@@ -3,7 +3,7 @@
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
-    "FalconForSequenceClassification"
+    "FalconForCausalLM"
   ],
   "attention_dropout": 0.0,
   "auto_map": {
@@ -29,23 +29,10 @@
   "num_hidden_layers": 32,
   "num_kv_heads": 71,
   "parallel_attn": true,
-  "problem_type": "single_label_classification",
-  "quantization_config": {
-    "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": false,
-    "load_in_8bit": true,
-    "quant_method": "bitsandbytes"
-  },
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.35.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 65024
 }