Upload config.json with huggingface_hub

config.json

@@ -12,13 +12,17 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 8192,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
     "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": false,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -34,7 +38,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.44.0",
   "use_cache": false,
   "vocab_size": 128256
 }