impl - model

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/BioGPT-Large-PubMedQA",
+  "activation_dropout": 0.0,
+  "architectures": [
+    "BioGptForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1600,
+  "initializer_range": 0.02,
+  "intermediate_size": 6400,
+  "layer_norm_eps": 1e-12,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "biogpt",
+  "num_attention_heads": 25,
+  "num_hidden_layers": 48,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 57726
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:180988fcdcdcbdccad2c2cc65346560b3e380b6054343f2ddc89c8218c135e14
+size 6285062518

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7afaf628e153fe2c34599507855c3d8b172a02287ad11bed4e1928a0c227977
+size 4472