based on cointegrated/rut5-small

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- 0.2.0
 ---
 
 # Model Card for Model ID

config.json

@@ -3,67 +3,30 @@
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "bos_token_id": 1,
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 1024,
   "d_kv": 64,
   "d_model": 512,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
-  "eos_token_id": 2,
-  "feed_forward_proj": "relu",
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": false,
-  "label2id": {
-    "LABEL_0": 0
-  },
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
-  "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
-  "output_past": true,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
-      "length_penalty": 2.0,
-      "max_length": 200,
-      "min_length": 30,
-      "no_repeat_ngram_size": 3,
-      "num_beams": 4,
-      "prefix": "summarize: "
-    },
-    "translation_en_to_de": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to German: "
-    },
-    "translation_en_to_fr": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to French: "
-    },
-    "translation_en_to_ro": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to Romanian: "
-    }
-  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
   "use_cache": true,
-  "vocab_size": 32100
+  "vocab_size": 20100
 }

generation_config.json

@@ -1,8 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
   "decoder_start_token_id": 0,
-  "eos_token_id": 2,
+  "eos_token_id": 1,
   "pad_token_id": 0,
   "transformers_version": "4.46.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aef572174e301737fe85125d5b19fea091c97b38c4fe9ac7a644cdb224617e4
-size 241984552
+oid sha256:27aaee9096dd0b5cdaf68206f589ba4bb6c783aa6ff05fb7c391653b7f452c3d
+size 258600360