Upload 4 files

conditional_gpt2_model.py

@@ -0,0 +1,43 @@
+from transformers import GPT2LMHeadModel
+
+class ConditionalGPT2LMHeadModel(GPT2LMHeadModel):        
+    def prepare_inputs_for_generation(self, input_ids, past_key_values=None, inputs_embeds=None, **kwargs):
+        # this is the same as `GPT2LMHeadModel` except `encoder_hidden_states` are added to inputs
+        
+        token_type_ids = kwargs.get("token_type_ids", None)
+        # only last token for inputs_ids if past is defined in kwargs
+        if past_key_values:
+            input_ids = input_ids[:, -1].unsqueeze(-1)
+            if token_type_ids is not None:
+                token_type_ids = token_type_ids[:, -1].unsqueeze(-1)
+
+        attention_mask = kwargs.get("attention_mask", None)
+        position_ids = kwargs.get("position_ids", None)
+
+        if attention_mask is not None and position_ids is None:
+            # create position_ids on the fly for batch generation
+            position_ids = attention_mask.long().cumsum(-1) - 1
+            position_ids.masked_fill_(attention_mask == 0, 1)
+            if past_key_values:
+                position_ids = position_ids[:, -1].unsqueeze(-1)
+        else:
+            position_ids = None
+
+        # if `inputs_embeds` are passed, we only want to use them in the 1st generation step
+        if inputs_embeds is not None and past_key_values is None:
+            model_inputs = {"inputs_embeds": inputs_embeds}
+        else:
+            model_inputs = {"input_ids": input_ids}
+            
+        model_inputs['encoder_hidden_states'] = kwargs.get('encoder_hidden_states', None)
+
+        model_inputs.update(
+            {
+                "past_key_values": past_key_values,
+                "use_cache": kwargs.get("use_cache"),
+                "position_ids": position_ids,
+                "attention_mask": attention_mask,
+                "token_type_ids": token_type_ids,
+            }
+        )
+        return model_inputs

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "mean_roberta/checkpoint-50000/",
+  "activation_function": "gelu_new",
+  "add_cross_attention": true,
+  "architectures": [
+    "ConditionalGPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "auto_map": {
+    "AutoModelForCausalLM": "conditional_gpt2_model.ConditionalGPT2LMHeadModel"
+  },
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 256,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 2707
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.28.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:995b549b74a984dc299582d9f444288d58380405d5441757f577e67a71d701e4
+size 236784093