Update config.json

config.json

@@ -1,4 +1,4 @@
-{
+LlamaConfig {
   "_name_or_path": "ZahrizhalAli/llama-7b-code-generation",
   "architectures": [
     "LlamaForCausalLM"
@@ -15,11 +15,24 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "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": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.31.0.dev0",
+  "transformers_version": "4.33.2",
   "use_cache": true,
   "vocab_size": 32000
 }