update model files

configuration_codet5p_bimodal.py

@@ -0,0 +1,76 @@
+# coding=utf-8
+# Copyright 2023 Salesforce authors, The EleutherAI, and HuggingFace Teams. All rights reserved.
+
+""" CodeT5+ bimodal model configuration"""
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+
+class CodeT5pBimodalConfig(PretrainedConfig):
+    model_type = "codet5p_bimodal"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    attribute_map = {"hidden_size": "d_model", "num_attention_heads": "num_heads", "num_hidden_layers": "num_layers"}
+
+    def __init__(
+            self,
+            vocab_size=32103,
+            d_model=768,
+            embed_dim=256,
+            d_kv=64,
+            d_ff=3072,
+            num_layers=12,
+            num_decoder_layers=None,
+            num_heads=12,
+            relative_attention_num_buckets=32,
+            relative_attention_max_distance=128,
+            dropout_rate=0.1,
+            layer_norm_epsilon=1e-6,
+            initializer_factor=1.0,
+            feed_forward_proj="relu",
+            is_encoder_decoder=False,
+            use_cache=True,
+            pad_token_id=0,
+            eos_token_id=2,
+            **kwargs
+    ):
+        self.vocab_size = vocab_size
+        self.d_model = d_model
+        self.embed_dim = embed_dim
+        self.d_kv = d_kv
+        self.d_ff = d_ff
+        self.num_layers = num_layers
+        self.num_decoder_layers = (
+            num_decoder_layers if num_decoder_layers is not None else self.num_layers
+        )  # default = symmetry
+        self.num_heads = num_heads
+        self.relative_attention_num_buckets = relative_attention_num_buckets
+        self.relative_attention_max_distance = relative_attention_max_distance
+        self.dropout_rate = dropout_rate
+        self.layer_norm_epsilon = layer_norm_epsilon
+        self.initializer_factor = initializer_factor
+        self.feed_forward_proj = feed_forward_proj
+        self.use_cache = use_cache
+
+        act_info = self.feed_forward_proj.split("-")
+        self.dense_act_fn = act_info[-1]
+        self.is_gated_act = act_info[0] == "gated"
+
+        if len(act_info) > 1 and act_info[0] != "gated" or len(act_info) > 2:
+            raise ValueError(
+                f"`feed_forward_proj`: {feed_forward_proj} is not a valid activation function of the dense layer."
+                "Please make sure `feed_forward_proj` is of the format `gated-{ACT_FN}` or `{ACT_FN}`, e.g. "
+                "'gated-gelu' or 'relu'"
+            )
+
+        # for backwards compatibility
+        if feed_forward_proj == "gated-gelu":
+            self.dense_act_fn = "gelu_new"
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            eos_token_id=eos_token_id,
+            is_encoder_decoder=is_encoder_decoder,
+            **kwargs,
+        )

modeling_codet5p_bimodal.py

@@ -0,0 +1,28 @@
+# coding=utf-8
+# Copyright 2023 Salesforce authors, The EleutherAI, and HuggingFace Teams. All rights reserved.
+""" PyTorch CodeT5+ matching models.
+The implementation is based on transformers.models.t5.modeling_t5 by adding a projection layer on T5EncoderModel
+"""
+
+from typing import Optional, Tuple, Union
+import torch
+from torch import nn
+import torch.nn.functional as F
+from transformers import T5ForConditionalGeneration
+from transformers.modeling_outputs import (
+    BaseModelOutput,
+)
+from configuration_codet5p_bimodal import CodeT5pBimodalConfig
+
+
+class CodeT5pBimodalModel(T5ForConditionalGeneration):
+    config_class = CodeT5pBimodalConfig
+
+    authorized_missing_keys = [
+        r"encoder.embed_tokens.weight",
+    ]
+
+    def __init__(self, config: CodeT5pBimodalConfig):
+        super().__init__(config)
+        self.proj = nn.Linear(config.d_model, config.embed_dim)
+        self.itm_head = nn.Linear(config.d_model, 2)