Update config.json

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "unsloth/Llama-3.2-3B-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -18,6 +19,21 @@
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "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": {
     "factor": 32.0,
@@ -29,7 +45,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.0.dev0",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 128256
-}
+}