init lfs

.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
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,69 @@
+{
+    "architectures": [
+        "DeepseekV3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+        "AutoModel": "modeling_deepseek.DeepseekV3Model",
+        "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+    },
+    "aux_loss_alpha": 0.001,
+    "bos_token_id": 0,
+    "eos_token_id": 1,
+    "ep_size": 1,
+    "first_k_dense_replace": 3,
+    "hidden_act": "silu",
+    "hidden_size": 7168,
+    "initializer_range": 0.02,
+    "intermediate_size": 18432,
+    "kv_lora_rank": 512,
+    "max_position_embeddings": 163840,
+    "model_type": "deepseek_v3",
+    "moe_intermediate_size": 2048,
+    "moe_layer_freq": 1,
+    "n_group": 8,
+    "n_routed_experts": 256,
+    "n_shared_experts": 1,
+    "norm_topk_prob": true,
+    "num_attention_heads": 128,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 61,
+    "num_key_value_heads": 128,
+    "num_nextn_predict_layers": 1,
+    "pretraining_tp": 1,
+    "q_lora_rank": 1536,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "beta_fast": 32,
+        "beta_slow": 1,
+        "factor": 40,
+        "mscale": 1.0,
+        "mscale_all_dim": 1.0,
+        "original_max_position_embeddings": 4096,
+        "type": "yarn"
+    },
+    "rope_theta": 10000,
+    "routed_scaling_factor": 2.5,
+    "scoring_func": "sigmoid",
+    "seq_aux": true,
+    "tie_word_embeddings": false,
+    "topk_group": 4,
+    "topk_method": "noaux_tc",
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.50.2",
+    "use_cache": false,
+    "v_head_dim": 128,
+    "vocab_size": 129280,
+    "quantization_config": {
+        "bits": 4,
+        "group_size": 64,
+        "modules_to_not_convert": null,
+        "quant_method": "awq",
+        "version": "gemm",
+        "zero_point": true
+    }
+}

configuration_deepseek.py

@@ -0,0 +1,210 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
+    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 DeepSeek-V3.
+
+    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 Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV3Model`]
+        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 DeepSeekV3 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 DeepseekV3Model, DeepseekV3Config
+
+    >>> # Initializing a Deepseek-V3 style configuration
+    >>> configuration = DeepseekV3Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=129280,
+        hidden_size=7168,
+        intermediate_size=18432,
+        moe_intermediate_size = 2048,
+        num_hidden_layers=61,
+        num_nextn_predict_layers=1,
+        num_attention_heads=128,
+        num_key_value_heads=128,
+        n_shared_experts = 1,
+        n_routed_experts = 256,
+        ep_size = 1,
+        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 = 3,
+        norm_topk_prob = True,
+        scoring_func = 'sigmoid',
+        aux_loss_alpha = 0.001,
+        seq_aux = True,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        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,
+        )

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.50.2"
+}

model-00001-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078e1fabb8c15a318ec5c7f4c018d0c7a2b172819b859826d0e37402d276a8a7
+size 4995076312

model-00002-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c373a3409342d4edc16e91f0ac1c747ce83895ddbcc567e72a444ff4ad57910
+size 4995320096

model-00003-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe80a8621bcf79eb477f2a14b7b4338ed759443d59d4e0f5a7c7579e52a42ef
+size 4993632760

model-00004-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99bb274934dae3703bd56dbcf43290acf77a5d317b3aa627ea90255c69f443d1
+size 4995319632

model-00005-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e10c9c14be4765a088a9d14ae56f291118fb56ca0b5b7be24c4f089fbe204a8f
+size 4995319632

model-00006-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ffecb179cc64e99d6adebe07ed01bcbd1a2c6a4b3242cd044f8a07b2f9314a4
+size 4995319680

model-00007-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7348cc5137b67bfff3f22ba8bcbf478ae911891418b24ec341fdff432ca1a6b3
+size 4995320096

model-00008-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d96eb6193acb6554b32182f960a3a9889e8a7587391cb5d8b519c5e8ac5d047
+size 4993632816

model-00009-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:850970fbc61bc5a6a0b5486b9bb51ce1e8d0a32adb1b0108bb31be3e7cd16203
+size 4995319632

model-00010-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66bb8677436f562f7c0194a685169df5d07fb965099f26ea8b33cb544cbe3a36
+size 4995321024

model-00011-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae378835a77c196cb8c4acd8a24dad341fe33313e167bfcbf95e6e16fe52388d
+size 4995321512

model-00012-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad80f14ea1a980a5faaf14b1b608ae058d1f1c79fc7d4322cb1e7ecfb97ec623
+size 4995321960

model-00013-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8b4af8ed3abad47652a9247a9e7f4e524046538155c0ffb94bfaa349610db6
+size 4955755456

model-00014-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:101580aa36eb038f6f95db15444eb49e30e8a25ba14ec021a24218ba67ceab88
+size 4993631600

model-00015-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4243d4ddad94780f63cf910121bd584df9b8634f0fe32905b36c5e65c652fe47
+size 4995321512

model-00016-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf64525f0cdd5ecef48e664b0a89776ba20cc8783ebddd786db8230b99e7650
+size 4995321512

model-00017-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52b3d8e41856cfe39b654e9943cfd449c865334a68ab5d60ccbd64450483ec5c
+size 4995321920

model-00018-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b43c18eece255bcee0294afae2ab056e92e3fe5324c3f438f66025d6b6d37e
+size 4995322024

model-00019-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d780a05db8102f8714e53fb46ddd889dd685dc83d2d996e844de6722e54a13
+size 4993634296

model-00020-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:505510a2539b4dd33babff24b9dab851a2e7331fc0541b926d98ca0aab3e4636
+size 4995321512

model-00021-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d92c9ef336993e11b366cfdb3b19576d2627ff29c53c8b5d3489732ddbf0a1
+size 4995321512

model-00022-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c897b58140729be61a99df6386dcda857c1fedf88f5f9ceda783ccf46aa710c
+size 4995321864

model-00023-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afa57803b7a9feb9de127fe11d308de0ef47d6f09c817d84fdc6be1f91142b9
+size 4995321968

model-00024-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a71fa9a882ded01528b05e250ecfcb4cf5e2293b898942566d3cc0bd50a8d3e
+size 4993634408

model-00025-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6198abb11d1560a116fb171ddc0cdac0507f66b9a567cdbd1a0062711254fe8
+size 4995321512

model-00026-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf1ecbf850014ab8161fce565116b1fe35f9f9bdb0229f136a8fdf61c5a44ac
+size 4995321512

model-00027-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130a524107cf03ba6ab263c9b2d50a034ccbfee81fcee4c7d83d92d6c71fb49c
+size 4995321808

model-00028-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d0712db29c7f0f336cb8829f1576440b09829c81f76e7d4a380f9b022a0ab8
+size 4995321968

model-00029-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c41abb2ae6ee3d989c38472339f8ee3e496747f14fc1947c47032dc772d0899
+size 4993634464

model-00030-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc0067c017bbb4990f5b2f4477b34b6485acfea7fb66254ead91c7127883abb7
+size 4995321512

model-00031-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825c784b451d23a7d6b56abd587247c4355e8c88a26bc20da58cb2d159cfd359
+size 4995321512

model-00032-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e969d8787ed736e595eac40855646e6801d84cd8d9b427dbe195a92139618b67
+size 4995321744

model-00033-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b81d170613edb8c403d537d151df2c43b38cca169c3ea953b392ebe044eba2e
+size 4995321968

model-00034-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b79093705aefa1bc97e0f41f71b55501970dd1d277dc5570b4a6137bccf042
+size 4993634520

model-00035-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99cd615cdc44ca4c740e03f88b2fee0577ff18fd398347edc0c5d37211e9e2c4
+size 4995321512

model-00036-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50b54c393515e60e1193f786e9bbc9626a8c267abd5c7f5a6de98fe9c595aaf4
+size 4995321512

model-00037-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77f67ee9729436004cd7810369952d7354972ff4d79ea66f83abdd0ffea4cd7
+size 4995321688

model-00038-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a278524228da5628779bbbbb8a779aebeb512dfc850f1005bf8c8d3eabb081fc
+size 4995321968

model-00039-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20da87df556fe52621e6698fa86ecad6fa8bb8979bac94d058e7fefe284eb43d
+size 4993634584

model-00040-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb7837667338dd4dc26b830b538ff28c0153c7f4c399ddbe1fe653c67d097b99
+size 4995321512

model-00041-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c1088fa030556288d200b5dd46e720cac3f1d26ba076a50968b6740b03c5b8
+size 4995321512

model-00042-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36912c6b6fa4604da6db220a54a704fb4f1a23cf5f8976cdfc1cfb2f8d0fa821
+size 4995321632

model-00043-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390b3acfff8d792a7b3983c8491757a3788c877ca1ff2f494142fa1b22ffbe1c
+size 4995321968

model-00044-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9d61c83e709a07edd9e62333f6b6969bd49b019c9b9c2449f7d5b22e72b4d22
+size 4993634632

model-00045-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64763cad2f099e81b015ce3826916a6b3b24eb676c9ec3183bae16ff2c05d93
+size 4995321512

model-00046-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9b2125c62aa0acffa19511e1e6abc171ada09332635c16c7c6b57cb3a3eeb5
+size 4995321512