Upload ProtNLA

config.json

@@ -1,170 +1,13 @@
 {
   "architectures": [
-    "EncoderDecoderModel"
+    "ProtNLA"
   ],
-  "decoder": {
-    "_name_or_path": "",
-    "add_cross_attention": true,
-    "architectures": null,
-    "attention_probs_dropout_prob": 0.2,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 0,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": 0,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "embedding_size": 768,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "silu",
-    "hidden_dropout_prob": 0.2,
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
-    "intermediate_size": 2048,
-    "is_decoder": true,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-12,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 1536,
-    "min_length": 0,
-    "model_type": "roformer",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 8,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 6,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 2,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "rotary_value": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "type_vocab_size": 2,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 16681
-  },
   "decoder_start_token_id": 0,
-  "encoder": {
-    "_name_or_path": "khairi/ProtFormer",
-    "add_cross_attention": false,
-    "architectures": [
-      "RoFormerForMaskedLM"
-    ],
-    "attention_probs_dropout_prob": 0.2,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "embedding_size": 768,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "silu",
-    "hidden_dropout_prob": 0.2,
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
-    "intermediate_size": 2048,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-12,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 1536,
-    "min_length": 0,
-    "model_type": "roformer",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 6,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 6,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 2,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "rotary_value": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": "float32",
-    "torchscript": false,
-    "type_vocab_size": 2,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 25005
-  },
+  "eos_token_id": 1,
   "is_encoder_decoder": true,
   "model_type": "encoder-decoder",
   "pad_token_id": 2,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.2",
-  "vocab_size": 16681
+  "transformers_version": "4.38.2",
+  "vocab_size": 10007
 }

generation_config.json

@@ -1,12 +1,12 @@
 {
   "bos_token_id": 0,
-  "do_sample": true,
   "eos_token_id": 1,
-  "max_new_tokens": 20,
-  "num_return_sequences": 5,
+  "max_new_tokens": 50,
+  "num_beans": 1,
   "output_logits": true,
   "output_scores": true,
   "pad_token_id": 2,
   "repetition_penalty": 1.3,
-  "transformers_version": "4.39.2"
+  "return_dict_in_generate": true,
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bce672bbf960b98736d425af3d4ddc6398e14fe94e1d6ff85b5e9293d7432f7
-size 453334260
+oid sha256:bf2a48e643fba9b8f1d887408536581f2b93a4fc1703a5599e9222b36ef763b1
+size 360315272