Upload model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "data/experiments/hf_output/checkpoint-31500",
+  "_name_or_path": "data/experiments/hf_output/checkpoint-500",
   "architectures": [
     "EncoderDecoderModel"
   ],
@@ -7,17 +7,18 @@
     "_name_or_path": "",
     "add_cross_attention": true,
     "architectures": null,
-    "attention_probs_dropout_prob": 0.6,
+    "attention_probs_dropout_prob": 0.2,
+    "ax_position_embeddings": 1024,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
-    "bos_token_id": 0,
+    "bos_token_id": 1,
     "chunk_size_feed_forward": 0,
     "cross_attention_hidden_size": null,
-    "decoder_start_token_id": 0,
+    "decoder_start_token_id": 1,
     "diversity_penalty": 0.0,
     "do_sample": false,
     "early_stopping": false,
-    "embedding_size": 512,
+    "embedding_size": 768,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": null,
     "exponential_decay_length_penalty": null,
@@ -25,14 +26,14 @@
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
     "hidden_act": "silu",
-    "hidden_dropout_prob": 0.6,
-    "hidden_size": 512,
+    "hidden_dropout_prob": 0.2,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
     "initializer_range": 0.02,
-    "intermediate_size": 1024,
+    "intermediate_size": 2048,
     "is_decoder": true,
     "is_encoder_decoder": false,
     "label2id": {
@@ -49,12 +50,12 @@
     "num_attention_heads": 8,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 12,
+    "num_hidden_layers": 6,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 2,
+    "pad_token_id": 3,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
@@ -79,68 +80,62 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 42316
+    "vocab_size": 15008
   },
-  "decoder_start_token_id": 0,
+  "decoder_start_token_id": 1,
   "encoder": {
-    "_name_or_path": "khairi/esm2_t12_35M_UR50D",
+    "_name_or_path": "",
     "add_cross_attention": false,
-    "architectures": [
-      "EsmModel"
-    ],
-    "attention_probs_dropout_prob": 0.5,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.2,
+    "ax_position_embeddings": 1024,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
     "bos_token_id": null,
     "chunk_size_feed_forward": 0,
-    "classifier_dropout": null,
     "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
     "early_stopping": false,
-    "emb_layer_norm_before": false,
+    "embedding_size": 768,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": null,
-    "esmfold_config": null,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.5,
-    "hidden_size": 480,
+    "hidden_act": "silu",
+    "hidden_dropout_prob": 0.2,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
     "initializer_range": 0.02,
-    "intermediate_size": 1920,
+    "intermediate_size": 2048,
     "is_decoder": false,
     "is_encoder_decoder": false,
-    "is_folding_model": false,
     "label2id": {
       "LABEL_0": 0,
       "LABEL_1": 1
     },
-    "layer_norm_eps": 1e-05,
+    "layer_norm_eps": 1e-12,
     "length_penalty": 1.0,
-    "mask_token_id": 32,
     "max_length": 20,
-    "max_position_embeddings": 1026,
+    "max_position_embeddings": 1536,
     "min_length": 0,
-    "model_type": "esm",
+    "model_type": "roformer",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 20,
+    "num_attention_heads": 8,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 12,
+    "num_hidden_layers": 6,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 1,
-    "position_embedding_type": "rotary",
+    "pad_token_id": 2,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
@@ -148,6 +143,7 @@
     "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,
@@ -155,23 +151,22 @@
     "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
-    "token_dropout": true,
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": "float32",
+    "torch_dtype": null,
     "torchscript": false,
+    "type_vocab_size": 2,
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_list": null,
-    "vocab_size": 33
+    "vocab_size": 25005
   },
-  "eos_token_id": 1,
+  "eos_token_id": 0,
   "is_encoder_decoder": true,
   "model_type": "encoder-decoder",
-  "pad_token_id": 2,
+  "pad_token_id": 3,
   "torch_dtype": "float32",
-  "transformers_version": "4.40.0",
-  "vocab_size": 42316
+  "transformers_version": "4.41.0",
+  "vocab_size": 15008
 }

generation_config.json

@@ -1,13 +1,13 @@
 {
-  "bos_token_id": 0,
-  "decoder_start_token_id": 0,
-  "eos_token_id": 1,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 0,
   "max_new_tokens": 50,
   "num_beans": 1,
   "output_logits": true,
   "output_scores": true,
-  "pad_token_id": 2,
+  "pad_token_id": 3,
   "repetition_penalty": 1.3,
   "return_dict_in_generate": true,
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.41.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af16ef5907dc87d011ae44f8e16b13d1e27a2d6a59decb8a513680d9f731c02
-size 376726500
+oid sha256:a97c71339674ff9888a7c8a3a31d86e9bcdfa1446982bfc0e71747e04d58bbdc
+size 447991496