Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,4 @@
+<s>{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "ApertusForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_apertus.ApertusConfig",
+    "AutoModel": "modeling_apertus.ApertusModel",
+    "AutoModelForCausalLM": "modeling_apertus.ApertusForCausalLM"
+  },
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 68,
+  "hidden_act": "xielu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 21504,
+  "max_position_embeddings": 65536,
+  "mlp_bias": false,
+  "model_type": "apertus",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 3,
+  "post_norm": false,
+  "qk_norm": true,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3",
+    "type": "llama3"
+  },
+  "rope_theta": 12000000,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "use_cache": false,
+  "vocab_size": 131072
+}

configuration_apertus.py

@@ -0,0 +1,217 @@
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#           This file was automatically generated from src/transformers/models/apertus/modular_apertus.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_apertus.py file directly. One of our CI enforces this.
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+# coding=utf-8
+# Copyright 2025 the HuggingFace Inc. team and the Swiss AI Initiative. 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.
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.modeling_rope_utils import rope_config_validation
+
+
+class ApertusConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`ApertusModel`]. It is used to instantiate a Apertus
+    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 Apertus-8B.
+    e.g. [swiss-ai/Apertus-8B](https://huggingface.co/swiss-ai/Apertus-8B)
+
+    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 131072):
+            Vocabulary size of the Apertus model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`ApertusModel`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 14336):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        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, check out [this
+            paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"xielu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 65536):
+            The maximum sequence length that this model might ever be used with. Apertus supports up to 65536 tokens.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-05):
+            The epsilon used by the rms normalization layers.
+        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`.
+        pad_token_id (`int`, *optional*, defaults to 3):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 12000000.0):
+            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
+        attention_bias (`bool`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import ApertusModel, ApertusConfig
+
+    >>> # Initializing a Apertus-8B style configuration
+    >>> configuration = ApertusConfig()
+
+    >>> # Initializing a model from the Apertus-8B style configuration
+    >>> model = ApertusModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "apertus"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    base_model_tp_plan = {
+        "layers.*.self_attn.q_proj": "colwise_rep",  # we need to replicate here due to the added norm on q and k
+        "layers.*.self_attn.k_proj": "colwise_rep",  # we need to replicate here due to the added norm on q and k
+        "layers.*.self_attn.v_proj": "colwise_rep",  # we need to replicate here due to the added norm on q and k
+        "layers.*.self_attn.o_proj": "rowwise_rep",  # we need to replicate here due to the added norm on q and k
+        "layers.*.mlp.up_proj": "colwise",
+        "layers.*.mlp.down_proj": "rowwise",
+        "layers.*.mlp.gate_proj": "colwise",
+    }
+    base_model_pp_plan = {
+        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
+        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
+        "norm": (["hidden_states"], ["hidden_states"]),
+    }
+
+    def __init__(
+        self,
+        vocab_size=131072,
+        hidden_size=4096,
+        intermediate_size=14336,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=None,
+        hidden_act="xielu",
+        max_position_embeddings=65536,
+        initializer_range=0.02,
+        rms_norm_eps=1e-5,
+        use_cache=True,
+        pad_token_id=3,
+        bos_token_id=1,
+        eos_token_id=2,
+        tie_word_embeddings=False,
+        rope_theta=12000000.0,
+        rope_scaling={
+            "rope_type": "llama3",
+            "factor": 8.0,
+            "original_max_position_embeddings": 8192,
+            "low_freq_factor": 1.0,
+            "high_freq_factor": 4.0,
+        },
+        attention_bias=False,
+        attention_dropout=0.0,
+        patches=["liger", "cce"],
+        **kwargs,
+    ):
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+        # Validate the correctness of rotary position embeddings parameters
+        # BC: if there is a 'type' field, copy it it to 'rope_type'.
+        if self.rope_scaling is not None and "type" in self.rope_scaling:
+            self.rope_scaling["rope_type"] = self.rope_scaling["type"]
+        rope_config_validation(self)
+
+        self.patches = patches
+
+
+__all__ = ["ApertusConfig"]

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    68
+  ],
+  "pad_token_id": 3,
+  "transformers_version": "4.56.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c21e1d777d7f5651191f50f3a873345c770fb49e384341d7e8584cd18f1402
+size 4999776656

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c2bd751b9c072de6cfeb97cc136d912b9d5cb2dcbbd9e30ed7b9cacb7f2b17
+size 4882374192

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681c4e64ea0ea9171df8a9e1c283d88253d2a70b7d278ef2d99ab1cd6bcdaf18
+size 4974647808

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a1187bf39f8a7b2045be7e3c142b4a7bd2967668fcfad802800d82d976b9b6d
+size 1249928160

model.safetensors.index.json

@@ -0,0 +1,459 @@
+{
+  "metadata": {
+    "total_parameters": 274496,
+    "total_size": 16106676480
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.act_fn.alpha_n": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.act_fn.alpha_p": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.act_fn.beta": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.act_fn.eps": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

modeling_apertus.py

@@ -0,0 +1,666 @@
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#           This file was automatically generated from src/transformers/models/apertus/modular_apertus.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_apertus.py file directly. One of our CI enforces this.
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+# coding=utf-8
+# Copyright 2025 the HuggingFace Inc. team and the Swiss AI Initiative. 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.
+from typing import Callable, Optional, Union
+
+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
+from transformers.masking_utils import create_causal_mask
+from transformers.modeling_layers import GenericForTokenClassification, 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.deprecation import deprecate_kwarg
+from transformers.utils.generic import check_model_inputs
+from .configuration_apertus import ApertusConfig
+
+try:
+    from liger_kernel.ops.rope import LigerRopeFunction
+    from liger_kernel.ops.rms_norm import LigerRMSNormFunction
+    ENABLE_LIGER = True
+except Exception as e:
+    print(f"Warning, could not import Liger packages, force disabling all Liger patches!\n{e}")
+    ENABLE_LIGER = False
+
+try:
+    from cut_cross_entropy import linear_cross_entropy
+    from typing import TypedDict
+    from dataclasses import dataclass
+    
+    class CCEPreset(TypedDict):
+        filter_eps: float | str | None
+        accum_e_fp32: bool
+        accum_c_fp32: bool
+        filter_e_grad: bool
+        filter_c_grad: bool
+    
+    class CCEKwargs(CCEPreset):
+        impl: str
+        reduction: str
+    
+    @dataclass
+    class PatchOptions:
+        impl: str
+        reduction: str
+        filter_eps: float | str | None
+        accum_e_fp32: bool
+        accum_c_fp32: bool
+        filter_e_grad: bool
+        filter_c_grad: bool
+        train_only: bool
+    
+        def to_kwargs(self) -> CCEKwargs:
+            return CCEKwargs(
+                impl=self.impl,
+                reduction=self.reduction,
+                filter_eps=self.filter_eps,
+                accum_e_fp32=self.accum_e_fp32,
+                accum_c_fp32=self.accum_c_fp32,
+                filter_e_grad=self.filter_e_grad,
+                filter_c_grad=self.filter_c_grad,
+            )
+    
+    _PATCH_OPTS = PatchOptions(
+            impl="cce",
+            reduction="mean",
+            filter_eps="auto",
+            accum_e_fp32=False,
+            accum_c_fp32=False,
+            filter_e_grad=True,
+            filter_c_grad=True,
+            train_only=False,
+    )
+    
+    def apply_lce(
+        e: torch.Tensor,
+        c: torch.Tensor,
+        labels: torch.Tensor,
+        opts,
+        bias: torch.Tensor | None = None,
+        **loss_kwargs,
+    ) -> torch.Tensor:
+        num_items_in_batch = loss_kwargs.get("num_items_in_batch", None)
+        cce_kwargs = opts.to_kwargs()
+        if num_items_in_batch is not None and cce_kwargs["reduction"] == "mean":
+            cce_kwargs["reduction"] = "sum"
+        else:
+            num_items_in_batch = None
+    
+        loss = linear_cross_entropy(
+            e,
+            c,
+            labels.to(e.device),
+            bias=bias,
+            shift=True,
+            **cce_kwargs,
+        )
+    
+        if num_items_in_batch is not None:
+            loss = loss / num_items_in_batch
+    
+        return loss
+    ENABLE_CCE = True
+except Exception as e:
+    print(f"Warning, could not import CCE packages, force disabling all CCE patches!\n{e}")
+    ENABLE_CCE = False
+
+class ApertusMLP(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.config = config
+        self.hidden_size = config.hidden_size
+        self.intermediate_size = config.intermediate_size
+        self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)
+        self.act_fn = ACT2FN[config.hidden_act]
+
+    def forward(self, x):
+        return self.down_proj(self.act_fn(self.up_proj(x)))
+
+
+@use_kernel_forward_from_hub("RMSNorm")
+class ApertusRMSNorm(nn.Module):
+    def __init__(self, hidden_size, eps=1e-6, **kwargs):
+        """
+        ApertusRMSNorm 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}"
+
+class ApertusLigerRMSNorm(nn.Module):
+    def __init__(
+        self,
+        hidden_size,
+        eps=1e-6,
+        offset=0.0,
+        casting_mode="llama",
+        in_place=True,
+        row_mode=None
+    ):
+        super().__init__()
+        self.weight = nn.Parameter(torch.ones(hidden_size))
+        self.variance_epsilon, self.offset, self.casting_mode, self.in_place, self.row_mode = (
+            eps,
+            offset,
+            casting_mode,
+            in_place,
+            row_mode,
+        )
+
+    def forward(self, hidden_states):
+        return LigerRMSNormFunction.apply(
+            hidden_states,
+            self.weight,
+            self.variance_epsilon,
+            self.offset,
+            self.casting_mode,
+            self.in_place,
+            self.row_mode,
+        )
+
+    def extra_repr(self):
+        return f"{tuple(self.weight.shape)}, eps={self.variance_epsilon}"
+
+class ApertusRotaryEmbedding(nn.Module):
+    inv_freq: torch.Tensor  # fix linting for `register_buffer`
+
+    def __init__(self, config: ApertusConfig, device=None):
+        super().__init__()
+        # BC: "rope_type" was originally "type"
+        if hasattr(config, "rope_scaling") and isinstance(config.rope_scaling, dict):
+            self.rope_type = config.rope_scaling.get("rope_type", config.rope_scaling.get("type"))
+        else:
+            self.rope_type = "default"
+        self.max_seq_len_cached = config.max_position_embeddings
+        self.original_max_seq_len = config.max_position_embeddings
+
+        self.config = config
+        self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
+
+        inv_freq, self.attention_scaling = self.rope_init_fn(self.config, device)
+        self.register_buffer("inv_freq", inv_freq, persistent=False)
+        self.original_inv_freq = self.inv_freq
+
+    @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 torch.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)
+
+
+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)
+
+
+def apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, 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.
+        position_ids (`torch.Tensor`, *optional*):
+            Deprecated and unused.
+        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 apply_liger_pos_emb(q, k, cos, sin, position_ids=None, 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.
+        position_ids (`torch.Tensor`, *optional*):
+            Deprecated and unused.
+        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.
+    """
+    return LigerRopeFunction.apply(q, k, cos, sin, position_ids, unsqueeze_dim)
+
+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: Optional[torch.Tensor],
+    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
+
+
+class ApertusAttention(nn.Module):
+    """Multi-headed attention from 'Attention Is All You Need' paper"""
+
+    def __init__(self, config: ApertusConfig, layer_idx: Optional[int] = None):
+        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=config.attention_bias
+        )
+        self.k_proj = nn.Linear(
+            config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.attention_bias
+        )
+        self.v_proj = nn.Linear(
+            config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.attention_bias
+        )
+        self.o_proj = nn.Linear(
+            config.num_attention_heads * self.head_dim, config.hidden_size, bias=config.attention_bias
+        )
+        if "liger" in config.patches and ENABLE_LIGER:
+            self.q_norm = ApertusLigerRMSNorm(self.head_dim, config.rms_norm_eps)
+            self.k_norm = ApertusLigerRMSNorm(self.head_dim, config.rms_norm_eps)
+            self._ROTARY = apply_liger_pos_emb
+        else:
+            self.q_norm = ApertusRMSNorm(self.head_dim, config.rms_norm_eps)
+            self.k_norm = ApertusRMSNorm(self.head_dim, config.rms_norm_eps)
+            self._ROTARY = apply_rotary_pos_emb
+
+    @deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58")
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        position_embeddings: tuple[torch.Tensor, torch.Tensor],
+        attention_mask: Optional[torch.Tensor],
+        past_key_values: Optional[Cache] = None,
+        cache_position: Optional[torch.LongTensor] = 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)
+        query_states = self.q_norm(query_states)
+        key_states = self.k_norm(key_states)
+
+        cos, sin = position_embeddings
+        query_states, key_states = self._ROTARY(query_states, key_states, cos, sin)
+
+        if past_key_values is not None:
+            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 = eager_attention_forward
+        if self.config._attn_implementation != "eager":
+            attention_interface = ALL_ATTENTION_FUNCTIONS[self.config._attn_implementation]
+
+        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.o_proj(attn_output)
+        return attn_output, attn_weights
+
+
+class ApertusDecoderLayer(GradientCheckpointingLayer):
+    def __init__(self, config: ApertusConfig, layer_idx: int):
+        super().__init__()
+        self.hidden_size = config.hidden_size
+
+        self.self_attn = ApertusAttention(config=config, layer_idx=layer_idx)
+
+        self.mlp = ApertusMLP(config)
+
+        if "liger" in config.patches and ENABLE_LIGER:
+            self.attention_layernorm = ApertusLigerRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+            self.feedforward_layernorm = ApertusLigerRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        else:
+            self.attention_layernorm = ApertusRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+            self.feedforward_layernorm = ApertusRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+
+    @deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58")
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[Cache] = None,
+        use_cache: Optional[bool] = False,
+        cache_position: Optional[torch.LongTensor] = None,
+        position_embeddings: Optional[tuple[torch.Tensor, torch.Tensor]] = None,
+        **kwargs: Unpack[TransformersKwargs],
+    ) -> tuple[torch.Tensor]:
+        residual = hidden_states
+        hidden_states = self.attention_layernorm(hidden_states)
+        hidden_states, _ = self.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.feedforward_layernorm(hidden_states)
+        hidden_states = self.mlp(hidden_states)
+        hidden_states = residual + hidden_states
+        return hidden_states
+
+
+@auto_docstring
+class ApertusPreTrainedModel(PreTrainedModel):
+    config: ApertusConfig
+    base_model_prefix = "model"
+    supports_gradient_checkpointing = True
+    _no_split_modules = ["ApertusDecoderLayer"]
+    _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": ApertusDecoderLayer,
+        "attentions": ApertusAttention,
+    }
+
+
+@auto_docstring
+class ApertusModel(ApertusPreTrainedModel):
+    def __init__(self, config: ApertusConfig):
+        super().__init__(config)
+        self.padding_idx = config.pad_token_id
+        self.vocab_size = config.vocab_size
+
+        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
+        self.layers = nn.ModuleList(
+            [ApertusDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
+        )
+
+        if "liger" in config.patches and ENABLE_LIGER:
+            self.norm = ApertusLigerRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+            print("Using Liger RMSNorm!")
+        else:
+            self.norm = ApertusRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.rotary_emb = ApertusRotaryEmbedding(config=config)
+        self.gradient_checkpointing = False
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    @check_model_inputs
+    @auto_docstring
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[Cache] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        cache_position: Optional[torch.LongTensor] = None,
+        use_cache: Optional[bool] = 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.embed_tokens(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(
+                past_seen_tokens, past_seen_tokens + inputs_embeds.shape[1], device=inputs_embeds.device
+            )
+
+        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_emb(hidden_states, position_ids)
+
+        for decoder_layer in self.layers[: self.config.num_hidden_layers]:
+            hidden_states = decoder_layer(
+                hidden_states,
+                attention_mask=causal_mask,
+                position_ids=position_ids,
+                past_key_values=past_key_values,
+                cache_position=cache_position,
+                position_embeddings=position_embeddings,
+                **kwargs,
+            )
+
+        hidden_states = self.norm(hidden_states)
+        return BaseModelOutputWithPast(
+            last_hidden_state=hidden_states,
+            past_key_values=past_key_values,
+        )
+
+
+@auto_docstring
+class ApertusForCausalLM(ApertusPreTrainedModel, GenerationMixin):
+    _tied_weights_keys = ["lm_head.weight"]
+    _tp_plan = {"lm_head": "colwise_rep"}
+    _pp_plan = {"lm_head": (["hidden_states"], ["logits"])}
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.config = config
+        self.model = ApertusModel(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: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[Cache] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = None,
+        use_cache: Optional[bool] = None,
+        cache_position: Optional[torch.LongTensor] = None,
+        logits_to_keep: Union[int, torch.Tensor] = 0,
+        **kwargs: Unpack[TransformersKwargs],
+    ) -> CausalLMOutputWithPast:
+        r"""
+        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
+            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
+            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
+            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
+
+        Example:
+
+        ```python
+        >>> from transformers import AutoTokenizer, ApertusForCausalLM
+
+        >>> model = ApertusForCausalLM.from_pretrained("swiss-ai/Apertus-8B")
+        >>> tokenizer = AutoTokenizer.from_pretrained("swiss-ai/Apertus-8B")
+
+        >>> prompt = "Hey, are you conscious? Can you talk to me?"
+        >>> inputs = tokenizer(prompt, return_tensors="pt")
+
+        >>> # Generate
+        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
+        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
+        ```"""
+        outputs: BaseModelOutputWithPast = self.model(
+            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
+        loss = None
+        logits = None
+
+        if "cce" in self.config.patches and ENABLE_CCE and labels is not None:
+            loss = apply_lce(
+                hidden_states,
+                self.lm_head.weight,
+                labels,
+                _PATCH_OPTS,
+                **kwargs,
+            )
+    
+            return CausalLMOutputWithPast(
+                loss=loss,
+                logits=logits,
+                past_key_values=outputs.past_key_values,
+                hidden_states=outputs.hidden_states,
+                attentions=outputs.attentions,
+            )
+        else:
+            # 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, :])
+    
+            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,
+            )
+
+
+class ApertusForTokenClassification(GenericForTokenClassification, ApertusPreTrainedModel):
+    pass
+
+
+__all__ = ["ApertusModel", "ApertusForCausalLM", "ApertusForTokenClassification", "ApertusPreTrainedModel"]

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b48362424d6314748c7d8a8d943e4e1a46552647ae9176b08d4f452e7b4313
+size 17078467