Upload folder using huggingface_hub

config.json

@@ -42,9 +42,24 @@
   "num_hidden_layers": 4,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "scale_embedding": false,
   "suppress_tokens": [],
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.41.1",
   "use_cache": true,
   "use_weighted_layer_sum": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8573cbe71fa4c903fe787bc065eef5d244a50e0d097680fd87fa785f9081a82
-size 151061672
+oid sha256:e008631c2eac939b0f7cf9c28375df7e726d29c3c767646c01908e59a0a0a898
+size 51832696