ikeno-ada
/

m2m100_418-mt-bitsandbytes-4bit

text2text-generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

ikeno-ada commited on Apr 3

Commit

d9c207e

•

1 Parent(s): c920108

Upload M2M100ForConditionalGeneration

Files changed (2) hide show

config.json +2 -2
generation_config.json +1 -1

config.json CHANGED Viewed

@@ -32,7 +32,7 @@
   "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,
@@ -46,7 +46,7 @@
   },
   "scale_embedding": true,
   "torch_dtype": "float16",
-  "transformers_version": "4.39.3",
   "use_cache": true,
   "vocab_size": 128112
 }

   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
   },
   "scale_embedding": true,
   "torch_dtype": "float16",
+  "transformers_version": "4.40.0.dev0",
   "use_cache": true,
   "vocab_size": 128112
 }

generation_config.json CHANGED Viewed

@@ -7,5 +7,5 @@
   "max_length": 200,
   "num_beams": 5,
   "pad_token_id": 1,
-  "transformers_version": "4.39.3"
 }

   "max_length": 200,
   "num_beams": 5,
   "pad_token_id": 1,
+  "transformers_version": "4.40.0.dev0"
 }