Training in progress, step 29

.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 @@
+{% 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 +1,47 @@
+{
+  "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": 50,
+  "num_key_value_heads": 8,
+  "pad_token_id": 3,
+  "patches": [
+    "liger",
+    "cce"
+  ],
+  "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": "4.57.1",
+  "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 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 68,
+  "pad_token_id": 3,
+  "transformers_version": "4.57.1",
+  "use_cache": false
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601445205aff0a8348e63ac8c4f8974522604a799581ae01c24a6b888741bb74
+size 4999776656

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b6ced143dfbc45ff0397391497171e24652af5f7f8892951ee60b57a3a9c30
+size 4882374192

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd32ff3dcd4672993614c21d2f954ed715d23a3dd7c509d00e43f5fa64a6cdf6
+size 4974647808

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c06320ffcdd1947789ab294adc72bd64611ac670c2a3626fa882af2aa533282
+size 4974664848

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84712aebb01895df27e147b879a6ae5c45f4ed7f815e552c038f747ec374b93
+size 4127332872

model.safetensors.index.json

@@ -0,0 +1,711 @@
+{
+  "metadata": {
+    "total_parameters": 11979358820,
+    "total_size": 23958717840
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.act_fn.alpha_n": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.act_fn.alpha_p": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.act_fn.beta": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.act_fn.eps": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.act_fn.alpha_n": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.act_fn.alpha_p": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.act_fn.beta": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.act_fn.eps": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.act_fn.alpha_n": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.act_fn.alpha_p": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.act_fn.beta": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.act_fn.eps": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.act_fn.alpha_n": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.act_fn.alpha_p": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.act_fn.beta": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.act_fn.eps": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.act_fn.alpha_n": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.act_fn.alpha_p": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.act_fn.beta": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.act_fn.eps": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.act_fn.alpha_n": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.act_fn.alpha_p": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.act_fn.beta": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.act_fn.eps": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.act_fn.alpha_n": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.act_fn.alpha_p": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.act_fn.beta": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.act_fn.eps": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.act_fn.alpha_n": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.act_fn.alpha_p": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.act_fn.beta": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.act_fn.eps": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.act_fn.alpha_n": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.act_fn.alpha_p": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.act_fn.beta": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.act_fn.eps": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.act_fn.alpha_n": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.act_fn.alpha_p": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.act_fn.beta": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.act_fn.eps": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.act_fn.alpha_n": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.act_fn.alpha_p": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.act_fn.beta": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.act_fn.eps": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.act_fn.alpha_n": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.act_fn.alpha_p": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.act_fn.beta": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.act_fn.eps": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.act_fn.alpha_n": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.act_fn.alpha_p": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.act_fn.beta": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.act_fn.eps": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.act_fn.alpha_n": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.act_fn.alpha_p": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.act_fn.beta": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.act_fn.eps": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.act_fn.alpha_n": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.act_fn.alpha_p": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.act_fn.beta": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.act_fn.eps": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.act_fn.alpha_n": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.act_fn.alpha_p": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.act_fn.beta": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.act_fn.eps": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.act_fn.alpha_n": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.act_fn.alpha_p": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.act_fn.beta": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.act_fn.eps": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.act_fn.alpha_n": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.act_fn.alpha_p": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.act_fn.beta": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.act_fn.eps": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.act_fn.alpha_n": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.act_fn.alpha_p": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.act_fn.beta": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.act_fn.eps": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.act_fn.alpha_n": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.act_fn.alpha_p": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.act_fn.beta": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.act_fn.eps": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.act_fn.alpha_n": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.act_fn.alpha_p": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.act_fn.beta": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.act_fn.eps": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.act_fn.alpha_n": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.act_fn.alpha_p": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.act_fn.beta": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.act_fn.eps": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.act_fn.alpha_n": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.act_fn.alpha_p": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.act_fn.beta": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.act_fn.eps": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.3.attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.act_fn.alpha_n": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.act_fn.alpha_p": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.act_fn.beta": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.act_fn.eps": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.act_fn.alpha_n": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.act_fn.alpha_p": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.act_fn.beta": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.act_fn.eps": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.4.attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.act_fn.alpha_n": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.act_fn.alpha_p": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.act_fn.beta": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.act_fn.eps": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.40.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.act_fn.alpha_n": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.act_fn.alpha_p": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.act_fn.beta": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.act_fn.eps": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.43.attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.act_fn.alpha_n": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.act_fn.alpha_p": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.act_fn.beta": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.act_fn.eps": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.act_fn.alpha_n": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.act_fn.alpha_p": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.act_fn.beta": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.act_fn.eps": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.act_fn.alpha_n": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.act_fn.alpha_p": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.act_fn.beta": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.act_fn.eps": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.act_fn.alpha_n": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.act_fn.alpha_p": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.act_fn.beta": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.act_fn.eps": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.act_fn.alpha_n": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.act_fn.alpha_p": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.act_fn.beta": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.act_fn.eps": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.48.attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.48.feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.48.mlp.act_fn.alpha_n": "model-00005-of-00005.safetensors",
+    "model.layers.48.mlp.act_fn.alpha_p": "model-00005-of-00005.safetensors",
+    "model.layers.48.mlp.act_fn.beta": "model-00005-of-00005.safetensors",
+    "model.layers.48.mlp.act_fn.eps": "model-00005-of-00005.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.48.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.48.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.49.attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.49.feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.49.mlp.act_fn.alpha_n": "model-00005-of-00005.safetensors",
+    "model.layers.49.mlp.act_fn.alpha_p": "model-00005-of-00005.safetensors",
+    "model.layers.49.mlp.act_fn.beta": "model-00005-of-00005.safetensors",
+    "model.layers.49.mlp.act_fn.eps": "model-00005-of-00005.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.49.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.49.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.act_fn.alpha_n": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.act_fn.alpha_p": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.act_fn.beta": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.act_fn.eps": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.act_fn.alpha_n": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.act_fn.alpha_p": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.act_fn.beta": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.act_fn.eps": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.act_fn.alpha_n": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.act_fn.alpha_p": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.act_fn.beta": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.act_fn.eps": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.act_fn.alpha_n": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.act_fn.alpha_p": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.act_fn.beta": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.act_fn.eps": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.act_fn.alpha_n": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.act_fn.alpha_p": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.act_fn.beta": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.act_fn.eps": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

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 sha256:355d635f647f0513296e01963d876dc5a10df2853296b11d5be7d00296070faf
+size 17078466

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08dd842896c230f73d6315514e9d44ffd267ee56af71df6039a023f6565581a0
+size 7633