Upload folder using huggingface_hub

config.json

@@ -42,6 +42,21 @@
   "num_hidden_layers": 4,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
+  "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"
+  },
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float16",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:017bf59d91a257ba04d953120a606719c61424b22dac3cccc54201862e68a9d4
-size 75540168
+oid sha256:ad2ed137bb4e1160256d3d0c20cbdea47216fbc3fe25727edfd5b0f991368b1d
+size 59174232