Upload folder using huggingface_hub

config.json

@@ -23,8 +23,23 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "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"
+  },
   "torch_dtype": "float16",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.43.4",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e77e732c1d49279fe062c0e3a825ddd191976cc1d5fe06c5bf11f4685e395953
-size 66741984
+oid sha256:a4c2ea476cbb1c2b8f45c859261153abe04e772d5f496f0b4f22d8978deb41ad
+size 45689616