Convert to fused experts for native transformers support (drop remote code)

config.json

@@ -4,11 +4,6 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "configuration_axk1.AXK1Config",
-    "AutoModel": "modeling_axk1.AXK1Model",
-    "AutoModelForCausalLM": "modeling_axk1.AXK1ForCausalLM"
-  },
   "aux_loss_alpha": 0.0001,
   "bos_token_id": 163691,
   "eos_token_id": 163691,
@@ -38,9 +33,9 @@
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000,
   "rope_scaling": {
-    "beta_fast": 32,
-    "beta_slow": 1,
-    "factor": 32,
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
     "mscale": 1.0,
     "mscale_all_dim": 1.0,
     "original_max_position_embeddings": 4096,
@@ -57,4 +52,4 @@
   "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 163840
-}
+}

configuration_axk1.py

@@ -1,209 +0,0 @@
-from transformers.configuration_utils import PretrainedConfig
-from transformers.utils import logging
-
-logger = logging.get_logger(__name__)
-
-AXK1_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
-class AXK1Config(PretrainedConfig):
-    r"""
-    This is the configuration class to store the configuration of a [`AXK1Model`]. It is used to instantiate an A.X
-    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 A.X K1.
-
-    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 129280):
-            Vocabulary size of the A.X K1 model. Defines the number of different tokens that can be represented by the
-            `inputs_ids` passed when calling [`AXK1Model`]
-        hidden_size (`int`, *optional*, defaults to 4096):
-            Dimension of the hidden representations.
-        intermediate_size (`int`, *optional*, defaults to 11008):
-            Dimension of the MLP representations.
-        moe_intermediate_size (`int`, *optional*, defaults to 1407):
-            Dimension of the MoE representations.
-        num_hidden_layers (`int`, *optional*, defaults to 32):
-            Number of hidden layers in the Transformer decoder.
-        num_nextn_predict_layers (`int`, *optional*, defaults to 1):
-            Number of nextn predict layers in the AXK1 Model.
-        num_attention_heads (`int`, *optional*, defaults to 32):
-            Number of attention heads for each attention layer in the Transformer decoder.
-        n_shared_experts (`int`, *optional*, defaults to None):
-            Number of shared experts, None means dense model.
-        n_routed_experts (`int`, *optional*, defaults to None):
-            Number of routed experts, None means dense model.
-        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
-            Scaling factor or routed experts.
-        topk_method (`str`, *optional*, defaults to `gready`):
-            Topk method used in routed gate.
-        n_group (`int`, *optional*, defaults to None):
-            Number of groups for routed experts.
-        topk_group (`int`, *optional*, defaults to None):
-            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
-        num_experts_per_tok (`int`, *optional*, defaults to None):
-            Number of selected experts, None means dense model.
-        moe_layer_freq (`int`, *optional*, defaults to 1):
-            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
-        first_k_dense_replace (`int`, *optional*, defaults to 0):
-            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
-                                                            \--k dense layers--/
-        norm_topk_prob (`bool`, *optional*, defaults to False):
-            Whether to normalize the weights of the routed experts.
-        scoring_func (`str`, *optional*, defaults to 'softmax'):
-            Method of computing expert weights.
-        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
-            Auxiliary loss weight coefficient.
-        seq_aux = (`bool`, *optional*, defaults to True):
-            Whether to compute the auxiliary loss for each individual sample.
-        num_key_value_heads (`int`, *optional*):
-            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
-            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
-            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
-            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
-            by meanpooling all the original heads within that group. For more details checkout [this
-            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
-            `num_attention_heads`.
-        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
-            The non-linear activation function (function or string) in the decoder.
-        max_position_embeddings (`int`, *optional*, defaults to 2048):
-            The maximum sequence length that this model might ever be used with.
-        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-06):
-            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*):
-            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.
-        pretraining_tp (`int`, *optional*, defaults to 1):
-            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
-            document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
-            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
-            issue](https://github.com/pytorch/pytorch/issues/76232).
-        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
-            Whether to tie weight embeddings
-        rope_theta (`float`, *optional*, defaults to 10000.0):
-            The base period of the RoPE embeddings.
-        rope_scaling (`Dict`, *optional*):
-            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
-            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
-            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
-            `max_position_embeddings` to the expected new maximum.
-        attention_bias (`bool`, defaults to `False`, *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 AXK1Model, AXK1Config
-
-    >>> # Initializing a A.X K1 style configuration
-    >>> configuration = AXK1Config()
-
-    >>> # Accessing the model configuration
-    >>> configuration = model.config
-    ```"""
-
-    model_type = "AXK1"
-    keys_to_ignore_at_inference = ["past_key_values"]
-
-    def __init__(
-        self,
-        vocab_size=163840,
-        hidden_size=7168,
-        intermediate_size=18432,
-        moe_intermediate_size = 2048,
-        num_hidden_layers=61,
-        num_nextn_predict_layers=1,
-        num_attention_heads=64,
-        num_key_value_heads=64,
-        n_shared_experts = 1,
-        n_routed_experts = 192,
-        ep_size = 8,
-        routed_scaling_factor = 2.5,
-        kv_lora_rank = 512,
-        q_lora_rank = 1536,
-        qk_rope_head_dim = 64,
-        v_head_dim = 128,
-        qk_nope_head_dim = 128,
-        topk_method = 'noaux_tc',
-        n_group = 8,
-        topk_group = 4,
-        num_experts_per_tok = 8,
-        moe_layer_freq = 1,
-        first_k_dense_replace = 1,
-        norm_topk_prob = True,
-        scoring_func = 'sigmoid',
-        aux_loss_alpha = 0.001,
-        seq_aux = True,
-        hidden_act="silu",
-        max_position_embeddings=131072,
-        initializer_range=0.02,
-        rms_norm_eps=1e-6,
-        use_cache=True,
-        pad_token_id=None,
-        bos_token_id=0,
-        eos_token_id=1,
-        pretraining_tp=1,
-        tie_word_embeddings=False,
-        rope_theta=10000.0,
-        rope_scaling=None,
-        attention_bias=False,
-        attention_dropout=0.0,
-        **kwargs,
-    ):
-        self.vocab_size = vocab_size
-        self.max_position_embeddings = max_position_embeddings
-        self.hidden_size = hidden_size
-        self.intermediate_size = intermediate_size
-        self.moe_intermediate_size = moe_intermediate_size
-        self.num_hidden_layers = num_hidden_layers
-        self.num_nextn_predict_layers = num_nextn_predict_layers
-        self.num_attention_heads = num_attention_heads
-        self.n_shared_experts = n_shared_experts
-        self.n_routed_experts = n_routed_experts
-        self.ep_size = ep_size
-        self.routed_scaling_factor = routed_scaling_factor
-        self.kv_lora_rank = kv_lora_rank
-        self.q_lora_rank = q_lora_rank
-        self.qk_rope_head_dim = qk_rope_head_dim
-        self.v_head_dim = v_head_dim
-        self.qk_nope_head_dim = qk_nope_head_dim
-        self.topk_method = topk_method
-        self.n_group = n_group
-        self.topk_group = topk_group
-        self.num_experts_per_tok = num_experts_per_tok
-        self.moe_layer_freq = moe_layer_freq
-        self.first_k_dense_replace = first_k_dense_replace
-        self.norm_topk_prob = norm_topk_prob
-        self.scoring_func = scoring_func
-        self.aux_loss_alpha = aux_loss_alpha
-        self.seq_aux = seq_aux
-        # 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.pretraining_tp = pretraining_tp
-        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
-
-        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,
-        )

model-00001-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a735fc10f35f9183cfa699e7695e0eb2cf2790d68e07eae86469ae711a1a2c10
-size 3986479336
+oid sha256:ca0ded32fc920d5e2ea7b23c062c1ceb7618bc07a7df0c9d847c991019f564ce
+size 20457509552

model-00002-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fe0bcb45d962ac5ec4dbff29cd91f879999a9aab67e3d749cf6f53f36e3e26a6
-size 3992994232

model-00003-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5ce8780bf44afdf6f8743e6e75acce93b507f59d1a5e7ce3ff98f84ee5c127db
-size 3992994248

model-00004-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b96425c0e81c515769c1f27c118f9cf6505fdcc3db4663f40c498748b45d5bdf
-size 3992994368

model-00005-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:164f86043b69d30953b0a8c090694f664741bf26cdc88695bb1ac9a69b078997
-size 3992994384

model-00006-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c06a66bebfa378ed4ca0665da9f9ef98a4bd2b4560cbf4c53f15eeb33a2788
-size 3992517472
+oid sha256:2ad77de05705933582f61b4d1071ef76734a1a87b88592bc3417f7e0687c4148
+size 17204559728

model-00007-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bc435c0b632d21495779d920c2f9a0a22198ad6151cfb7a4d33b2583366f79e8
-size 3992994248

model-00008-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:082409ae90152a25e2d06f99b4e70fe45701d2e91de8aaebb660ba500c00166b
-size 3992994328

model-00009-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1949c2327c505e37d16f79f1797171af0cf8c2f9a667589dbd8159715a719a81
-size 3992994384

model-00010-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2bf987ac945472cdfcc0d8910a6dc3d80551a99a7152d119fab33466b429723
-size 3992517520
+oid sha256:9e7405893edecdf328f95dab910b65f675882e4130678ee64b29cdf60974d1f2
+size 17204559728

model-00011-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:004b6958e80aac36285fecd7a6d453f932fae5f1bf2e4072777742f81932e930
-size 3992994248

model-00012-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dbed5bab4f26757b99048a1a142c34c1757dcf8e8b9391eebf6c43e68fc91263
-size 3992994288

model-00013-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5f1ff84f637c78e83ddc090150630856c66e041f7ce6db4f919896ffae1d4849
-size 3992994384

model-00014-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c3e5f65bbcc3ab83f3053673cde8017b2468e9fb1241409549e1be7ccf15e3
-size 3992517568
+oid sha256:ccd1111a74f365f08ae46f056d42ce7b00dcbf6d6460d1bc3344d62f84c1a9b7
+size 17204559728

model-00015-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cd4c43bb4abd0df948b6dceaf360be50a5c0c067eacb5a3fe4e486daa85d62f0
-size 3992994240

model-00016-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:65a00af0f3870f9cc042ae2c563acbd658299bf28ec904026ad92fe9eee4ead6
-size 3992994248

model-00017-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:474c2c959e8f0578bfa8db0e918db4e6ed0bbddff85b5b69fca76545018a639b
-size 3992994384

model-00018-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ffd34d5686c37184e3913cbc74c392697e2f59576f3a6257c35079f6e8326cbd
-size 3992994384

model-00019-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e91122b6aaad9ee4f04b8945bf61a59cc10b7d4ece53492782d567fb7bbd522
-size 3992517464
+oid sha256:d2899e4549037e50d366d48dc4c5cfd15b5f2d116cd41edba1fbd78890acab75
+size 17204559728

model-00020-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0b5afa754c1065747ab0b6a167f197035c89f52dee1dd67dca0f97e05a2667e8
-size 3992994248

model-00021-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:44153248a71ed44fc2957174f771d97de632db70dc24ccd6d3e54aac5a94bd70
-size 3992994336

model-00022-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0abd76b458a035ea2fd5832d2893ec6a21db3cdee523d9372f91c41c20cd5f2c
-size 3992994384

model-00023-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e1ec1a7ef5c4c59c11f1c983d91dea43b88aa07e1d86f58a8f2217af5f475d
-size 3992517512
+oid sha256:401538e51b47359eac1cabfac98162400caf1abcde979bfd03944cd978666b1c
+size 17204559728

model-00024-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1d1c7af49919466fb993f1bde6cbe8d94ac878645e6fc2e1eba7b499157ed8ea
-size 3992994248

model-00025-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:92f978ebadb2aa100ca0c55a67baa5efcdb953ab1c251a1d6b7dbd516f1171c1
-size 3992994296

model-00026-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:df53f73479e5ddc76db295c9e71043dc366418c39cc6b0ebff813ab3cd6f5835
-size 3992994384

model-00027-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254227ecf8264573882c30463f3485369e391f55a12eb5d25461a4d7fef66693
-size 3992517552
+oid sha256:b50913bcf200a62f155dfcfff88628fce60c550f3ba8c71db9a4b986a18111f8
+size 17204559728

model-00028-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1324db399dfa9fb82feba7d755a5993372b9aa7b975a42a8a50805250d12363a
-size 3992994248

model-00029-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fa079b850646bd1b7266e732a505542c24f22c9d39ad05fb5e8141ba1fd0abab
-size 3992994256

model-00030-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cbbd6837a3281d0ab6839f0a62f78a6cfe87fc46ff6c11739bcacaf0a0b8f119
-size 3992994384

model-00031-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f00627dc9ac95d533d2d0e7f4cc25c5192403ea0ba5fad749d78778f110a855b
-size 3995790352
+oid sha256:aa5b94d1651696f38cdc653ca026137fb28610e30dfd8890a8f870d9d002b1b0
+size 90876712

model-00032-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7993843bb287338dc0d2a1a903b517cb7d53d3bc2c1b4debf42c58123081f87d
-size 3989721488
+oid sha256:bf3dff50b3397816de13eafe31e0d1650f7e2f053ddbc29f81185aaa9477c179
+size 17113683024

model-00033-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19139be74a17924ab266ca2d30abedd381f76ddab28ef9419a075e8206691fa0
-size 3992994248

model-00034-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cd7f924ae3d3465c04d3e28d7af1941bc232faacd4ae772f91708261866b1401
-size 3992994344

model-00035-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e308f25d88bcfc8dd119106fe9f9b69050045b181c36b03851e0805321ca834b
-size 3992994384

model-00036-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa9cd2cbf7c9d6422e4cbf85a2b3a6be34e8dc49636cc5cbfa4c2fe132d8d8d
-size 3992517496
+oid sha256:79b6693ab04dfa39de197483b05ebf2463b131bb95d9268a2782c24f71938275
+size 17204559728

model-00037-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b0a9087a2c94fce2aec4cef3c420fac9ff0f31a31c145ce8885e9fb4c7c6d7e9
-size 3992994248

model-00038-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5ac2afb8ff27684218afb064307ea7538d56bc4b136d8693965b7207235e7384
-size 3992994304

model-00039-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:395ca7d39cd2ada5fff3fe9f72557e5de8495c458bfdaaea1c44e3c0526306ed
-size 3992994384

model-00040-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ced152d89b4bee3280b09e4dfba6a481e94a374b37fd4b2f2687dcde4de3986
-size 3992517600
+oid sha256:46a649edc54259c017dd1883b1e2283095194bda77e4fa4841c5bca70774916b
+size 17204559784

model-00041-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:00cef7eba75f78210be972648320f8fd38e8d078a7b3050d08ccc703d9a4dfa7
-size 3992994384

model-00042-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0be06d51c86ec1ec1435871d33f08ed7f97c3a5c73215b5ea0d453ea857e937c
-size 3992994400

model-00043-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:65262fc0ffdab9b48830a46f0d99f1ee5c73b9f7acb14187f18d0f1d4b6125cf
-size 3992994520

model-00044-of-00260.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c6386160eb24feec5ddd2e753921d097da05218dabccc5803f3be7a338b43eb
-size 3992517752
+oid sha256:070506c065947cd0fd4a21600f69320aed46930c28572635dd2b0182bb5061ec
+size 17204559744

model-00045-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6cf8465147b6ec52ae4fa955494ea873c7aaa5666864ee3586b9699842ef2977
-size 3992994360

model-00046-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:10d380531b81e2cc967fb38f7dc4e3155449adab0c149d0ae742e95244f457e7
-size 3992994384

model-00047-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9ba264c98c8e4e666fe6f520a687f8ac4716102d3065fd64e686a52b89042cba
-size 3992994496

model-00048-of-00260.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6ace00fc142016778a0db5c866c1047f127516ed85ab691b0ae12c7e92c8990e
-size 3992994520