Upload Flitto/tmp_expertQA_exaone3.5-7.8b_exp2_finance_fullft final/

chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '[|system|][|endofturn|]
+' }}{% endif %}{{ '[|' + message['role'] + '|]' + message['content'] }}{% if message['role'] == 'user' %}{{ '
+' }}{% else %}{{ '[|endofturn|]
+' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '[|assistant|]' }}{% endif %}

config.json

@@ -0,0 +1,40 @@
+{
+  "activation_function": "silu",
+  "architectures": [
+    "ExaoneForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_exaone.ExaoneConfig",
+    "AutoModelForCausalLM": "modeling_exaone.ExaoneForCausalLM",
+    "AutoModelForSequenceClassification": "modeling_exaone.ExaoneForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "embed_dropout": 0.0,
+  "eos_token_id": 361,
+  "head_dim": 128,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 32768,
+  "model_type": "exaone",
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "num_layers": 32,
+  "pad_token_id": 0,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 1000000.0,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 1000000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
+  "vocab_size": 102400
+}

configuration_exaone.py

@@ -0,0 +1,197 @@
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#           This file was automatically generated from src/transformers/models/exaone/modular_exaone.py.
+#               Do NOT edit this file manually as any edits will be overwritten by the generation of
+#             the file from the modular. If any change should be done, please apply the change to the
+#                          modular_exaone.py file directly. One of our CI enforces this.
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+# Copyright 2026 The LG AI Research and HuggingFace Inc. team. All rights reserved.
+#
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""LG AI Research EXAONE Lab"""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.modeling_rope_utils import RopeParameters
+
+
+class ExaoneConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`ExaoneModel`]. It is used to
+    instantiate a EXAONE model according to the specified arguments, defining the model architecture. Instantiating a
+    configuration with the defaults will yield a similar configuration to that of the EXAONE-3.0-7.8B-Instruct [LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct)
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model
+    outputs. Read the documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 102400):
+            Vocabulary size of the EXAONE model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`ExaoneModel`]. Vocabulary size of the model.
+            Defines the different tokens that can be represented by the `inputs_ids` passed to the forward method of
+            [`ExaoneModel`].
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
+        hidden_size (`int`, *optional*, defaults to 2048):
+            Dimensionality of the encoder layers and the pooler layer.
+        num_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        intermediate_size (`int`, *optional*, defaults to `hidden_size * 4`):
+            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
+        activation_function (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
+            and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
+            accordingly.
+            Expected contents:
+                `rope_type` (`str`):
+                    The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
+                    'llama3'], with 'default' being the original RoPE implementation.
+                `factor` (`float`, *optional*):
+                    Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
+                    most scaling types, a `factor` of x will enable the model to handle sequences of length x *
+                    original maximum pre-trained length.
+                `original_max_position_embeddings` (`int`, *optional*):
+                    Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
+                    pretraining.
+                `attention_factor` (`float`, *optional*):
+                    Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
+                    computation. If unspecified, it defaults to value recommended by the implementation, using the
+                    `factor` field to infer the suggested value.
+                `beta_fast` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 32.
+                `beta_slow` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 1.
+                `short_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to short contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `long_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to long contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `low_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
+                `high_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
+        embed_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        layer_norm_epsilon (`float`, *optional*, defaults to 1e-05):
+            The epsilon used by the layer normalization layers.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if ``config.is_decoder=True``.
+        bos_token_id (`int`, *optional*, defaults to 0):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+
+    Example:
+
+    ```python
+    >>> from transformers import EXAONEModel, ExaoneConfig
+
+    >>> # Initializing a EXAONE configuration
+    >>> configuration = ExaoneConfig()
+
+    >>> # Initializing a model from configuration
+    >>> model = EXAONEModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "exaone"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    attribute_map = {
+        "num_hidden_layers": "num_layers",
+        "hidden_act": "activation_function",
+        "rms_norm_eps": "layer_norm_epsilon",
+    }
+
+    def __init__(
+        self,
+        vocab_size: int | None = 102400,
+        max_position_embeddings=2048,
+        hidden_size: int | None = 2048,
+        num_layers: int | None = 32,
+        num_attention_heads: int | None = 32,
+        num_key_value_heads: int | None = None,
+        intermediate_size: int | None = None,
+        activation_function: str | None = "silu",
+        rope_parameters: RopeParameters | None = None,
+        embed_dropout: float | None = 0.0,
+        attention_dropout: float | None = 0.0,
+        layer_norm_epsilon: float | None = 1e-5,
+        initializer_range: float | None = 0.02,
+        use_cache: bool | None = True,
+        bos_token_id: int | None = 0,
+        eos_token_id: int | None = 2,
+        pad_token_id: int | None = None,
+        tie_word_embeddings: bool | None = False,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.num_layers = num_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_layers = num_layers
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+        self.num_key_value_heads = num_key_value_heads
+        if intermediate_size:
+            self.intermediate_size = intermediate_size
+        else:
+            self.intermediate_size = hidden_size * 4
+        self.activation_function = activation_function
+        self.embed_dropout = embed_dropout
+        self.attention_dropout = attention_dropout
+        self.layer_norm_epsilon = layer_norm_epsilon
+        self.initializer_range = initializer_range
+        self.use_cache = use_cache
+        self.rope_parameters = rope_parameters
+
+        self.bos_token_id = bos_token_id
+        self.eos_token_id = eos_token_id
+        self.pad_token_id = pad_token_id
+        self.tie_word_embeddings = tie_word_embeddings
+
+        super().__init__(**kwargs)
+
+
+__all__ = ["ExaoneConfig"]

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    361
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.7.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1520762a8a530b621b55cbe4b8593793f5110ac9011e559e8e49f7575fc6acd
+size 15636931624

modeling_exaone.py

@@ -0,0 +1,543 @@
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#           This file was automatically generated from src/transformers/models/exaone/modular_exaone.py.
+#               Do NOT edit this file manually as any edits will be overwritten by the generation of
+#             the file from the modular. If any change should be done, please apply the change to the
+#                          modular_exaone.py file directly. One of our CI enforces this.
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+# Copyright 2026 The LG AI Research and HuggingFace Inc. team. All rights reserved.
+#
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""LG AI Research EXAONE Lab"""
+
+from collections.abc import Callable
+from typing import Optional
+
+import torch
+from torch import nn
+
+from transformers.activations import ACT2FN
+from transformers.cache_utils import Cache, DynamicCache
+from transformers.generation import GenerationMixin
+from transformers.integrations import use_kernel_forward_from_hub, use_kernel_func_from_hub, use_kernelized_func
+from transformers.masking_utils import create_causal_mask
+from transformers.modeling_layers import GradientCheckpointingLayer
+from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast
+from transformers.modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_update
+from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
+from transformers.processing_utils import Unpack
+from transformers.utils import TransformersKwargs, auto_docstring, can_return_tuple
+from transformers.utils.generic import check_model_inputs, maybe_autocast
+from .configuration_exaone import ExaoneConfig
+
+
+@use_kernel_forward_from_hub("RMSNorm")
+class ExaoneRMSNorm(nn.Module):
+    def __init__(self, hidden_size, eps=1e-6):
+        """
+        ExaoneRMSNorm is equivalent to T5LayerNorm
+        """
+        super().__init__()
+        self.weight = nn.Parameter(torch.ones(hidden_size))
+        self.variance_epsilon = eps
+
+    def forward(self, hidden_states):
+        input_dtype = hidden_states.dtype
+        hidden_states = hidden_states.to(torch.float32)
+        variance = hidden_states.pow(2).mean(-1, keepdim=True)
+        hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
+        return self.weight * hidden_states.to(input_dtype)
+
+    def extra_repr(self):
+        return f"{tuple(self.weight.shape)}, eps={self.variance_epsilon}"
+
+
+def rotate_half(x):
+    """Rotates half the hidden dims of the input."""
+    x1 = x[..., : x.shape[-1] // 2]
+    x2 = x[..., x.shape[-1] // 2 :]
+    return torch.cat((-x2, x1), dim=-1)
+
+
+@use_kernel_func_from_hub("rotary_pos_emb")
+def apply_rotary_pos_emb(q, k, cos, sin, unsqueeze_dim=1):
+    """Applies Rotary Position Embedding to the query and key tensors.
+
+    Args:
+        q (`torch.Tensor`): The query tensor.
+        k (`torch.Tensor`): The key tensor.
+        cos (`torch.Tensor`): The cosine part of the rotary embedding.
+        sin (`torch.Tensor`): The sine part of the rotary embedding.
+        unsqueeze_dim (`int`, *optional*, defaults to 1):
+            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
+            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
+            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
+            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
+            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
+            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
+    Returns:
+        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
+    """
+    cos = cos.unsqueeze(unsqueeze_dim)
+    sin = sin.unsqueeze(unsqueeze_dim)
+    q_embed = (q * cos) + (rotate_half(q) * sin)
+    k_embed = (k * cos) + (rotate_half(k) * sin)
+    return q_embed, k_embed
+
+
+def repeat_kv(hidden_states: torch.Tensor, n_rep: int) -> torch.Tensor:
+    """
+    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
+    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
+    """
+    batch, num_key_value_heads, slen, head_dim = hidden_states.shape
+    if n_rep == 1:
+        return hidden_states
+    hidden_states = hidden_states[:, :, None, :, :].expand(batch, num_key_value_heads, n_rep, slen, head_dim)
+    return hidden_states.reshape(batch, num_key_value_heads * n_rep, slen, head_dim)
+
+
+def eager_attention_forward(
+    module: nn.Module,
+    query: torch.Tensor,
+    key: torch.Tensor,
+    value: torch.Tensor,
+    attention_mask: torch.Tensor | None,
+    scaling: float,
+    dropout: float = 0.0,
+    **kwargs: Unpack[TransformersKwargs],
+):
+    key_states = repeat_kv(key, module.num_key_value_groups)
+    value_states = repeat_kv(value, module.num_key_value_groups)
+
+    attn_weights = torch.matmul(query, key_states.transpose(2, 3)) * scaling
+    if attention_mask is not None:
+        causal_mask = attention_mask[:, :, :, : key_states.shape[-2]]
+        attn_weights = attn_weights + causal_mask
+
+    attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query.dtype)
+    attn_weights = nn.functional.dropout(attn_weights, p=dropout, training=module.training)
+    attn_output = torch.matmul(attn_weights, value_states)
+    attn_output = attn_output.transpose(1, 2).contiguous()
+
+    return attn_output, attn_weights
+
+
+@use_kernelized_func(apply_rotary_pos_emb)
+class ExaoneAttention(nn.Module):
+    """Multi-headed attention from 'Attention Is All You Need' paper"""
+
+    def __init__(self, config: ExaoneConfig, layer_idx: int):
+        super().__init__()
+        self.config = config
+        self.layer_idx = layer_idx
+        self.head_dim = getattr(config, "head_dim", config.hidden_size // config.num_attention_heads)
+        self.num_key_value_groups = config.num_attention_heads // config.num_key_value_heads
+        self.scaling = self.head_dim**-0.5
+        self.attention_dropout = config.attention_dropout
+        self.is_causal = True
+        self.q_proj = nn.Linear(config.hidden_size, config.num_attention_heads * self.head_dim, bias=False)
+        self.k_proj = nn.Linear(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=False)
+        self.v_proj = nn.Linear(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=False)
+        self.out_proj = nn.Linear(config.num_attention_heads * self.head_dim, config.hidden_size, bias=False)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        position_embeddings: tuple[torch.Tensor, torch.Tensor] | None = None,
+        attention_mask: torch.Tensor | None = None,
+        past_key_values: Cache | None = None,
+        cache_position: torch.LongTensor | None = None,
+        **kwargs: Unpack[TransformersKwargs],
+    ) -> tuple[torch.Tensor, torch.Tensor]:
+        input_shape = hidden_states.shape[:-1]
+        hidden_shape = (*input_shape, -1, self.head_dim)
+
+        query_states = self.q_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+        key_states = self.k_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+        value_states = self.v_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+
+        cos, sin = position_embeddings
+        query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin)
+
+        if past_key_values is not None:
+            # sin and cos are specific to RoPE models; cache_position needed for the static cache
+            cache_kwargs = {"sin": sin, "cos": cos, "cache_position": cache_position}
+            key_states, value_states = past_key_values.update(key_states, value_states, self.layer_idx, cache_kwargs)
+
+        attention_interface: Callable = ALL_ATTENTION_FUNCTIONS.get_interface(
+            self.config._attn_implementation, eager_attention_forward
+        )
+
+        attn_output, attn_weights = attention_interface(
+            self,
+            query_states,
+            key_states,
+            value_states,
+            attention_mask,
+            dropout=0.0 if not self.training else self.attention_dropout,
+            scaling=self.scaling,
+            **kwargs,
+        )
+
+        attn_output = attn_output.reshape(*input_shape, -1).contiguous()
+        attn_output = self.out_proj(attn_output)
+        return attn_output, attn_weights
+
+
+class ExaoneAttentionBlock(nn.Module):
+    """Dummy wrapper class for EXAONE 3.5 structure"""
+
+    def __init__(self, config: ExaoneConfig, layer_idx: int):
+        super().__init__()
+        self.config = config
+        self.layer_idx = layer_idx
+        self.attention = ExaoneAttention(config, layer_idx)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        position_embeddings: tuple[torch.Tensor, torch.Tensor] | None = None,
+        attention_mask: torch.Tensor | None = None,
+        past_key_values: Cache | None = None,
+        cache_position: torch.LongTensor | None = None,
+        **kwargs: Unpack[TransformersKwargs],
+    ) -> tuple[torch.Tensor, torch.Tensor]:
+        return self.attention(
+            hidden_states=hidden_states,
+            position_embeddings=position_embeddings,
+            attention_mask=attention_mask,
+            past_key_values=past_key_values,
+            cache_position=cache_position,
+            **kwargs,
+        )
+
+
+class ExaoneMLP(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.config = config
+        self.hidden_size = config.hidden_size
+        self.intermediate_size = config.intermediate_size
+        self.c_fc_0 = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.c_fc_1 = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.c_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)
+        self.act = ACT2FN[config.hidden_act]
+
+    def forward(self, x):
+        output_proj = self.c_proj(self.act(self.c_fc_0(x)) * self.c_fc_1(x))
+        return output_proj
+
+
+class ExaoneDecoderLayer(GradientCheckpointingLayer):
+    def __init__(self, config, layer_id):
+        super().__init__()
+        self.config = config
+        self.hidden_size = config.hidden_size
+        self.ln_1 = ExaoneRMSNorm(hidden_size=self.hidden_size, eps=config.layer_norm_epsilon)
+        self.attn = ExaoneAttentionBlock(config, layer_id)
+        self.ln_2 = ExaoneRMSNorm(hidden_size=self.hidden_size, eps=config.layer_norm_epsilon)
+        self.mlp = ExaoneMLP(config)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        attention_mask: torch.Tensor | None = None,
+        position_ids: torch.LongTensor | None = None,
+        past_key_values: Cache | None = None,
+        use_cache: bool | None = False,
+        cache_position: torch.LongTensor | None = None,
+        position_embeddings: tuple[torch.Tensor, torch.Tensor] | None = None,
+        **kwargs: Unpack[TransformersKwargs],
+    ) -> torch.Tensor:
+        residual = hidden_states
+        hidden_states = self.ln_1(hidden_states)
+        # Self Attention
+        hidden_states, _ = self.attn(
+            hidden_states=hidden_states,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_values=past_key_values,
+            use_cache=use_cache,
+            cache_position=cache_position,
+            position_embeddings=position_embeddings,
+            **kwargs,
+        )
+        hidden_states = residual + hidden_states
+
+        # Fully Connected
+        residual = hidden_states
+        hidden_states = self.ln_2(hidden_states)
+        hidden_states = self.mlp(hidden_states)
+        hidden_states = residual + hidden_states
+        return hidden_states
+
+
+@auto_docstring
+class ExaonePreTrainedModel(PreTrainedModel):
+    config: ExaoneConfig
+
+    base_model_prefix = "transformer"
+    supports_gradient_checkpointing = True
+    _no_split_modules = ["ExaoneDecoderLayer"]
+    _skip_keys_device_placement = ["past_key_values"]
+    _supports_flash_attn = True
+    _supports_sdpa = True
+    _supports_flex_attn = True
+
+    _can_compile_fullgraph = True
+    _supports_attention_backend = True
+    _can_record_outputs = {
+        "hidden_states": ExaoneDecoderLayer,
+        "attentions": ExaoneAttention,
+    }
+
+
+class ExaoneRotaryEmbedding(nn.Module):
+    inv_freq: torch.Tensor  # fix linting for `register_buffer`
+
+    def __init__(self, config: ExaoneConfig, device=None):
+        super().__init__()
+        self.max_seq_len_cached = config.max_position_embeddings
+        self.original_max_seq_len = config.max_position_embeddings
+
+        self.config = config
+
+        self.rope_type = self.config.rope_parameters["rope_type"]
+        rope_init_fn: Callable = self.compute_default_rope_parameters
+        if self.rope_type != "default":
+            rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
+        inv_freq, self.attention_scaling = rope_init_fn(self.config, device)
+
+        self.register_buffer("inv_freq", inv_freq, persistent=False)
+        self.register_buffer("original_inv_freq", inv_freq.clone(), persistent=False)
+
+    @staticmethod
+    def compute_default_rope_parameters(
+        config: ExaoneConfig | None = None,
+        device: Optional["torch.device"] = None,
+        seq_len: int | None = None,
+    ) -> tuple["torch.Tensor", float]:
+        """
+        Computes the inverse frequencies according to the original RoPE implementation
+        Args:
+            config ([`~transformers.PreTrainedConfig`]):
+                The model configuration.
+            device (`torch.device`):
+                The device to use for initialization of the inverse frequencies.
+            seq_len (`int`, *optional*):
+                The current sequence length. Unused for this type of RoPE.
+        Returns:
+            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
+            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
+        """
+        base = config.rope_parameters["rope_theta"]
+        dim = getattr(config, "head_dim", None) or config.hidden_size // config.num_attention_heads
+
+        attention_factor = 1.0  # Unused in this type of RoPE
+
+        # Compute the inverse frequencies
+        inv_freq = 1.0 / (
+            base ** (torch.arange(0, dim, 2, dtype=torch.int64).to(device=device, dtype=torch.float) / dim)
+        )
+        return inv_freq, attention_factor
+
+    @torch.no_grad()
+    @dynamic_rope_update  # power user: used with advanced RoPE types (e.g. dynamic rope)
+    def forward(self, x, position_ids):
+        inv_freq_expanded = self.inv_freq[None, :, None].float().expand(position_ids.shape[0], -1, 1).to(x.device)
+        position_ids_expanded = position_ids[:, None, :].float()
+
+        device_type = x.device.type if isinstance(x.device.type, str) and x.device.type != "mps" else "cpu"
+        with maybe_autocast(device_type=device_type, enabled=False):  # Force float32
+            freqs = (inv_freq_expanded.float() @ position_ids_expanded.float()).transpose(1, 2)
+            emb = torch.cat((freqs, freqs), dim=-1)
+            cos = emb.cos() * self.attention_scaling
+            sin = emb.sin() * self.attention_scaling
+
+        return cos.to(dtype=x.dtype), sin.to(dtype=x.dtype)
+
+
+@auto_docstring
+class ExaoneModel(ExaonePreTrainedModel):
+    def __init__(self, config: ExaoneConfig):
+        super().__init__(config)
+        self.config = config
+        self.hidden_size = config.hidden_size
+        self.padding_idx = config.pad_token_id
+        self.vocab_size = config.vocab_size
+
+        self.wte = nn.Embedding(self.vocab_size, self.hidden_size, self.padding_idx)
+        self.drop = nn.Dropout(float(config.embed_dropout))
+        self.h = nn.ModuleList([ExaoneDecoderLayer(config, layer_id=i) for i in range(config.num_layers)])
+        self.ln_f = ExaoneRMSNorm(hidden_size=self.hidden_size, eps=config.layer_norm_epsilon)
+        self.rotary = ExaoneRotaryEmbedding(config)
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    @check_model_inputs
+    @auto_docstring
+    def forward(
+        self,
+        input_ids: torch.LongTensor | None = None,
+        attention_mask: torch.Tensor | None = None,
+        position_ids: torch.LongTensor | None = None,
+        past_key_values: Cache | None = None,
+        inputs_embeds: torch.FloatTensor | None = None,
+        cache_position: torch.LongTensor | None = None,
+        use_cache: bool | None = None,
+        **kwargs: Unpack[TransformersKwargs],
+    ) -> BaseModelOutputWithPast:
+        if (input_ids is None) ^ (inputs_embeds is not None):
+            raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
+
+        if inputs_embeds is None:
+            inputs_embeds: torch.Tensor = self.wte(input_ids)
+
+        if use_cache and past_key_values is None:
+            past_key_values = DynamicCache(config=self.config)
+
+        if cache_position is None:
+            past_seen_tokens = past_key_values.get_seq_length() if past_key_values is not None else 0
+            cache_position: torch.Tensor = (
+                torch.arange(inputs_embeds.shape[1], device=inputs_embeds.device) + past_seen_tokens
+            )
+
+        if position_ids is None:
+            position_ids = cache_position.unsqueeze(0)
+
+        causal_mask = create_causal_mask(
+            config=self.config,
+            input_embeds=inputs_embeds,
+            attention_mask=attention_mask,
+            cache_position=cache_position,
+            past_key_values=past_key_values,
+            position_ids=position_ids,
+        )
+
+        hidden_states = inputs_embeds
+        position_embeddings = self.rotary(hidden_states, position_ids=position_ids)
+
+        for decoder_layer in self.h[: self.config.num_layers]:
+            hidden_states = decoder_layer(
+                hidden_states,
+                attention_mask=causal_mask,
+                position_embeddings=position_embeddings,
+                position_ids=position_ids,
+                past_key_values=past_key_values,
+                use_cache=use_cache,
+                cache_position=cache_position,
+                **kwargs,
+            )
+
+        hidden_states = self.ln_f(hidden_states)
+        return BaseModelOutputWithPast(
+            last_hidden_state=hidden_states,
+            past_key_values=past_key_values,
+        )
+
+
+@auto_docstring
+class ExaoneForCausalLM(ExaonePreTrainedModel, GenerationMixin):
+    _tied_weights_keys = {"lm_head.weight": "transformer.wte.weight"}
+    _tp_plan = {"lm_head": "colwise_gather_output"}
+    _pp_plan = {"lm_head": (["hidden_states"], ["logits"])}
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.transformer = ExaoneModel(config)
+        self.vocab_size = config.vocab_size
+        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    @can_return_tuple
+    @auto_docstring
+    def forward(
+        self,
+        input_ids: torch.LongTensor | None = None,
+        attention_mask: torch.Tensor | None = None,
+        position_ids: torch.LongTensor | None = None,
+        past_key_values: Cache | None = None,
+        inputs_embeds: torch.FloatTensor | None = None,
+        labels: torch.LongTensor | None = None,
+        use_cache: bool | None = None,
+        cache_position: torch.LongTensor | None = None,
+        logits_to_keep: int | torch.Tensor = 0,
+        **kwargs: Unpack[TransformersKwargs],
+    ) -> CausalLMOutputWithPast:
+        r"""
+        Args:
+            labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
+                Labels for language modeling. Note that the labels **are shifted** inside the model, i.e. you can set
+                `labels = input_ids` Indices are selected in `[-100, 0, ..., config.vocab_size]` All labels set to `-100`
+                are ignored (masked), the loss is only computed for labels in `[0, ..., config.vocab_size]`
+
+        Example:
+
+        ```python
+        >>> from transformers import AutoModelForCausalLM, AutoTokenizer
+
+        >>> model = AutoModelForCausalLM.from_pretrained("LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct",
+                                                         trust_remote_code=True)
+        >>> tokenizer = AutoTokenizer.from_pretrained("LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct")
+
+        >>> prompt = "Explain how wonderful you are"
+        >>> messages = [
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": prompt}
+        ]
+        >>> input_ids = tokenizer.apply_chat_template(
+            messages,
+            tokenize=True,
+            add_generation_prompt=True,
+            return_tensors="pt"
+        )
+
+        >>> output = model.generate(**input_ids.to(model.device), max_new_tokens=128)
+        >>> tokenizer.decode(output[0], skip_special_tokens=True)
+        '[|system|]You are a helpful assistant.\n[|user|]Explain how wonderful you are\n[|assistant|]As an AI assistant, I don\'t experience feelings or qualities like "wonderfulness" in the way humans do, but I can certainly highlight several aspects that make my capabilities and interactions valuable and beneficial:\n\n1. **Knowledge and Information**: I am equipped with extensive knowledge across a wide range of topics including science, technology, history, culture, and more. This allows me to provide accurate, informative responses to a vast array of inquiries, helping users learn and explore new ideas.\n\n2. **Accessibility**: I am available 24/7, meaning you can ask me questions or seek assistance at'
+        ```
+        """
+        outputs: BaseModelOutputWithPast = self.transformer(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_values=past_key_values,
+            inputs_embeds=inputs_embeds,
+            use_cache=use_cache,
+            cache_position=cache_position,
+            **kwargs,
+        )
+
+        hidden_states = outputs.last_hidden_state
+        # Only compute necessary logits, and do not upcast them to float if we are not computing the loss
+        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
+        logits = self.lm_head(hidden_states[:, slice_indices, :])
+
+        loss = None
+        if labels is not None:
+            loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size, **kwargs)
+
+        return CausalLMOutputWithPast(
+            loss=loss,
+            logits=logits,
+            past_key_values=outputs.past_key_values,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+        )
+
+
+__all__ = ["ExaonePreTrainedModel", "ExaoneModel", "ExaoneForCausalLM"]

tokenizer_config.json

@@ -0,0 +1,326 @@
+{
+  "add_prefix_space": false,
+  "additional_special_token": [
+    "[unused0]",
+    "[unused1]",
+    "[unused2]",
+    "[unused3]",
+    "[unused4]",
+    "[unused5]",
+    "[unused6]",
+    "[unused7]",
+    "[unused8]",
+    "[unused9]",
+    "[unused10]",
+    "[unused11]",
+    "[unused12]",
+    "[unused13]",
+    "[unused14]",
+    "[unused15]",
+    "[unused16]",
+    "[unused17]",
+    "[unused18]",
+    "[unused19]",
+    "[unused20]",
+    "[unused21]",
+    "[unused22]",
+    "[unused23]",
+    "[unused24]",
+    "[unused25]",
+    "[unused26]",
+    "[unused27]",
+    "[unused28]",
+    "[unused29]",
+    "[unused30]",
+    "[unused31]",
+    "[unused32]",
+    "[unused33]",
+    "[unused34]",
+    "[unused35]",
+    "[unused36]",
+    "[unused37]",
+    "[unused38]",
+    "[unused39]",
+    "[unused40]",
+    "[unused41]",
+    "[unused42]",
+    "[unused43]",
+    "[unused44]",
+    "[unused45]",
+    "[unused46]",
+    "[unused47]",
+    "[unused48]",
+    "[unused49]",
+    "[unused50]",
+    "[unused51]",
+    "[unused52]",
+    "[unused53]",
+    "[unused54]",
+    "[unused55]",
+    "[unused56]",
+    "[unused57]",
+    "[unused58]",
+    "[unused59]",
+    "[unused60]",
+    "[unused61]",
+    "[unused62]",
+    "[unused63]",
+    "[unused64]",
+    "[unused65]",
+    "[unused66]",
+    "[unused67]",
+    "[unused68]",
+    "[unused69]",
+    "[unused70]",
+    "[unused71]",
+    "[unused72]",
+    "[unused73]",
+    "[unused74]",
+    "[unused75]",
+    "[unused76]",
+    "[unused77]",
+    "[unused78]",
+    "[unused79]",
+    "[unused80]",
+    "[unused81]",
+    "[unused82]",
+    "[unused83]",
+    "[unused84]",
+    "[unused85]",
+    "[unused86]",
+    "[unused87]",
+    "[unused88]",
+    "[unused89]",
+    "[unused90]",
+    "[unused91]",
+    "[unused92]",
+    "[unused93]",
+    "[unused94]",
+    "[unused95]",
+    "[unused96]",
+    "[unused97]",
+    "[unused98]",
+    "[unused99]",
+    "[extra_id_0]",
+    "[extra_id_1]",
+    "[extra_id_2]",
+    "[extra_id_3]",
+    "[extra_id_4]",
+    "[extra_id_5]",
+    "[extra_id_6]",
+    "[extra_id_7]",
+    "[extra_id_8]",
+    "[extra_id_9]",
+    "[extra_id_10]",
+    "[extra_id_11]",
+    "[extra_id_12]",
+    "[extra_id_13]",
+    "[extra_id_14]",
+    "[extra_id_15]",
+    "[extra_id_16]",
+    "[extra_id_17]",
+    "[extra_id_18]",
+    "[extra_id_19]",
+    "[extra_id_20]",
+    "[extra_id_21]",
+    "[extra_id_22]",
+    "[extra_id_23]",
+    "[extra_id_24]",
+    "[extra_id_25]",
+    "[extra_id_26]",
+    "[extra_id_27]",
+    "[extra_id_28]",
+    "[extra_id_29]",
+    "[extra_id_30]",
+    "[extra_id_31]",
+    "[extra_id_32]",
+    "[extra_id_33]",
+    "[extra_id_34]",
+    "[extra_id_35]",
+    "[extra_id_36]",
+    "[extra_id_37]",
+    "[extra_id_38]",
+    "[extra_id_39]",
+    "[extra_id_40]",
+    "[extra_id_41]",
+    "[extra_id_42]",
+    "[extra_id_43]",
+    "[extra_id_44]",
+    "[extra_id_45]",
+    "[extra_id_46]",
+    "[extra_id_47]",
+    "[extra_id_48]",
+    "[extra_id_49]",
+    "[extra_id_50]",
+    "[extra_id_51]",
+    "[extra_id_52]",
+    "[extra_id_53]",
+    "[extra_id_54]",
+    "[extra_id_55]",
+    "[extra_id_56]",
+    "[extra_id_57]",
+    "[extra_id_58]",
+    "[extra_id_59]",
+    "[extra_id_60]",
+    "[extra_id_61]",
+    "[extra_id_62]",
+    "[extra_id_63]",
+    "[extra_id_64]",
+    "[extra_id_65]",
+    "[extra_id_66]",
+    "[extra_id_67]",
+    "[extra_id_68]",
+    "[extra_id_69]",
+    "[extra_id_70]",
+    "[extra_id_71]",
+    "[extra_id_72]",
+    "[extra_id_73]",
+    "[extra_id_74]",
+    "[extra_id_75]",
+    "[extra_id_76]",
+    "[extra_id_77]",
+    "[extra_id_78]",
+    "[extra_id_79]",
+    "[extra_id_80]",
+    "[extra_id_81]",
+    "[extra_id_82]",
+    "[extra_id_83]",
+    "[extra_id_84]",
+    "[extra_id_85]",
+    "[extra_id_86]",
+    "[extra_id_87]",
+    "[extra_id_88]",
+    "[extra_id_89]",
+    "[extra_id_90]",
+    "[extra_id_91]",
+    "[extra_id_92]",
+    "[extra_id_93]",
+    "[extra_id_94]",
+    "[extra_id_95]",
+    "[extra_id_96]",
+    "[extra_id_97]",
+    "[extra_id_98]",
+    "[extra_id_99]",
+    "[extra_id_100]",
+    "[extra_id_101]",
+    "[extra_id_102]",
+    "[extra_id_103]",
+    "[extra_id_104]",
+    "[extra_id_105]",
+    "[extra_id_106]",
+    "[extra_id_107]",
+    "[extra_id_108]",
+    "[extra_id_109]",
+    "[extra_id_110]",
+    "[extra_id_111]",
+    "[extra_id_112]",
+    "[extra_id_113]",
+    "[extra_id_114]",
+    "[extra_id_115]",
+    "[extra_id_116]",
+    "[extra_id_117]",
+    "[extra_id_118]",
+    "[extra_id_119]",
+    "[extra_id_120]",
+    "[extra_id_121]",
+    "[extra_id_122]",
+    "[extra_id_123]",
+    "[extra_id_124]",
+    "[extra_id_125]",
+    "[extra_id_126]",
+    "[extra_id_127]",
+    "[extra_id_128]",
+    "[extra_id_129]",
+    "[extra_id_130]",
+    "[extra_id_131]",
+    "[extra_id_132]",
+    "[extra_id_133]",
+    "[extra_id_134]",
+    "[extra_id_135]",
+    "[extra_id_136]",
+    "[extra_id_137]",
+    "[extra_id_138]",
+    "[extra_id_139]",
+    "[extra_id_140]",
+    "[extra_id_141]",
+    "[extra_id_142]",
+    "[extra_id_143]",
+    "[extra_id_144]",
+    "[extra_id_145]",
+    "[extra_id_146]",
+    "[extra_id_147]",
+    "[extra_id_148]",
+    "[extra_id_149]",
+    "[extra_id_150]",
+    "[extra_id_151]",
+    "[extra_id_152]",
+    "[extra_id_153]",
+    "[extra_id_154]",
+    "[extra_id_155]",
+    "[extra_id_156]",
+    "[extra_id_157]",
+    "[extra_id_158]",
+    "[extra_id_159]",
+    "[extra_id_160]",
+    "[extra_id_161]",
+    "[extra_id_162]",
+    "[extra_id_163]",
+    "[extra_id_164]",
+    "[extra_id_165]",
+    "[extra_id_166]",
+    "[extra_id_167]",
+    "[extra_id_168]",
+    "[extra_id_169]",
+    "[extra_id_170]",
+    "[extra_id_171]",
+    "[extra_id_172]",
+    "[extra_id_173]",
+    "[extra_id_174]",
+    "[extra_id_175]",
+    "[extra_id_176]",
+    "[extra_id_177]",
+    "[extra_id_178]",
+    "[extra_id_179]",
+    "[extra_id_180]",
+    "[extra_id_181]",
+    "[extra_id_182]",
+    "[extra_id_183]",
+    "[extra_id_184]",
+    "[extra_id_185]",
+    "[extra_id_186]",
+    "[extra_id_187]",
+    "[extra_id_188]",
+    "[extra_id_189]",
+    "[extra_id_190]",
+    "[extra_id_191]",
+    "[extra_id_192]",
+    "[extra_id_193]",
+    "[extra_id_194]",
+    "[extra_id_195]",
+    "[extra_id_196]",
+    "[extra_id_197]",
+    "[extra_id_198]",
+    "[|endofturn|]",
+    "PI:URL",
+    "PI:EMAIL",
+    "PI:ACCOUNT_NUM",
+    "PI:PHONE_NUM",
+    "PI:BUSINESS_NUM",
+    "PI:ANNON",
+    "PI:KEY",
+    "PI:ID",
+    "PI:IP_ADDRESS",
+    "PI:USER"
+  ],
+  "backend": "tokenizers",
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "[|endofturn|]",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "[UNK]"
+}