Upload T5ForConditionalGeneration

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "google-t5/t5-base",
   "architectures": [
-    "T5Model"
+    "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 3072,
@@ -23,21 +23,6 @@
   "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
-  "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"
-  },
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "task_specific_params": {
@@ -69,8 +54,8 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "torch_dtype": "float16",
-  "transformers_version": "4.40.2",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab7e7780578355ff07fe0b4256d4e489f39d6a00f9b0b99a67b3d738f2f2d25
-size 418397616
+oid sha256:185537a7defe66d3d601b13ae1f0e05f079aa454847cbce9e49224ab9566f941
+size 891644712