Upload model

config.json

@@ -1,24 +1,39 @@
 {
-  "_name_or_path": "Rostlab/prot_bert",
+  "_name_or_path": "nferruz/ProtGPT2",
+  "activation_function": "gelu_new",
   "architectures": [
-    "BertForMaskedLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.0,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1024,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 40000,
-  "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 30,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
   "transformers_version": "4.46.3",
-  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30
+  "vocab_size": 67965
 }

generation_config.json

@@ -1,5 +1,6 @@
 {
   "_from_model_config": true,
-  "pad_token_id": 0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
   "transformers_version": "4.46.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06dc39ff43fdbb5c5a4fdabff11e16bff869cb09e51ba945afbf01af8b7cd13d
-size 1752394624
+oid sha256:584abd0c130ec76da2a5d32862f8167194d1e05b20d9d34f27d1a8ed0fbbfe4c
+size 3186830888