Upload BlenderbotForConditionalGeneration

config.json

@@ -1,33 +1,64 @@
 {
-  "_name_or_path": "google/flan-t5-large",
+  "_name_or_path": "facebook/blenderbot-400M-distill",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
   "architectures": [
-    "T5ForConditionalGeneration"
+    "BlenderbotForConditionalGeneration"
   ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
-  "d_ff": 2816,
-  "d_kv": 64,
-  "d_model": 1024,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
-  "initializer_factor": 1.0,
+  "d_model": 1280,
+  "decoder_attention_heads": 32,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 1,
+  "do_blenderbot_90_layernorm": true,
+  "dropout": 0.1,
+  "encoder_attention_heads": 32,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 2,
+  "encoder_no_repeat_ngram_size": 3,
+  "eos_token_id": 2,
+  "extra_layer_norm": false,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
   "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "n_positions": 512,
-  "num_decoder_layers": 24,
-  "num_heads": 16,
-  "num_layers": 24,
-  "output_past": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layernorm_variant": "prelayernorm",
+  "length_penalty": 0.65,
+  "max_length": 60,
+  "max_position_embeddings": 128,
+  "min_length": 20,
+  "model_type": "blenderbot",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": true,
+  "normalize_embedding": false,
+  "num_beams": 10,
+  "num_hidden_layers": 2,
   "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
+  "unk_token_id": 3,
   "use_cache": true,
-  "vocab_size": 32128
+  "vocab_size": 8008
 }

generation_config.json

@@ -1,7 +1,15 @@
 {
   "_from_model_config": true,
-  "decoder_start_token_id": 0,
-  "eos_token_id": 1,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "encoder_no_repeat_ngram_size": 3,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "length_penalty": 0.65,
+  "max_length": 60,
+  "min_length": 20,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 10,
   "pad_token_id": 0,
   "transformers_version": "4.44.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473e1f8c9a16420b1fe5be89bcf1395a8418894d414f75217f701fe542089d60
-size 3132668808
+oid sha256:e2438e5b50e1f8eabde5a9b5fe128799a1c438bde27e29b863e03f44bc646757
+size 1459283800