swap for non-int8 version

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-medium.en",
+  "_name_or_path": "/shared/models/LEVI_LoFi_v2_MediumEN_Lora_Int8",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -25,13 +25,18 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 24,
   "eos_token_id": 50256,
-  "forced_decoder_ids": null,
+  "forced_decoder_ids": [
+    [
+      1,
+      50362
+    ]
+  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
-  "mask_feature_length": 30,
-  "mask_feature_min_masks": 2,
-  "mask_feature_prob": 0.05,
-  "mask_time_length": 40,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
   "max_length": 448,
@@ -42,22 +47,101 @@
   "num_hidden_layers": 24,
   "num_mel_bins": 80,
   "pad_token_id": 50256,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float32",
-    "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": [],
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    357,
+    366,
+    438,
+    532,
+    685,
+    705,
+    796,
+    930,
+    1058,
+    1220,
+    1267,
+    1279,
+    1303,
+    1343,
+    1377,
+    1391,
+    1635,
+    1782,
+    1875,
+    2162,
+    2361,
+    2488,
+    3467,
+    4008,
+    4211,
+    4600,
+    4808,
+    5299,
+    5855,
+    6329,
+    7203,
+    9609,
+    9959,
+    10563,
+    10786,
+    11420,
+    11709,
+    11907,
+    13163,
+    13697,
+    13700,
+    14808,
+    15306,
+    16410,
+    16791,
+    17992,
+    19203,
+    19510,
+    20724,
+    22305,
+    22935,
+    27007,
+    30109,
+    30420,
+    33409,
+    34949,
+    40283,
+    40493,
+    40549,
+    47282,
+    49146,
+    50257,
+    50357,
+    50358,
+    50359,
+    50360,
+    50361
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.32.1",
+  "transformers_version": "4.34.0",
   "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51864

generation_config.json

@@ -185,6 +185,6 @@
     50360,
     50361
   ],
-  "transformers_version": "4.32.1",
+  "transformers_version": "4.34.0",
   "use_cache": false
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e553c346e8f7c65be71f73a9741a6f00d24327c9344bfb043e3c972296f02a1
-size 3055738070
+oid sha256:a7f66ea872fb5330ebabaaacdd61889156ec6bc203cc6040bd27096cf084fa7e
+size 3055737561