MXFP4 file-quant model

.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 +1,125 @@
+{
+    "_attn_implementation_autoset": false,
+    "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": 163584,
+    "dtype": "bfloat16",
+    "eos_token_id": 163586,
+    "ep_size": 1,
+    "first_k_dense_replace": 1,
+    "hidden_act": "silu",
+    "hidden_size": 7168,
+    "initializer_range": 0.02,
+    "intermediate_size": 18432,
+    "kv_lora_rank": 512,
+    "max_position_embeddings": 262144,
+    "model_type": "deepseek_v3",
+    "moe_intermediate_size": 2048,
+    "moe_layer_freq": 1,
+    "n_group": 1,
+    "n_routed_experts": 384,
+    "n_shared_experts": 1,
+    "norm_topk_prob": true,
+    "num_attention_heads": 64,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 61,
+    "num_key_value_heads": 64,
+    "num_nextn_predict_layers": 0,
+    "pad_token_id": 163839,
+    "pretraining_tp": 1,
+    "q_lora_rank": 1536,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "beta_fast": 1.0,
+        "beta_slow": 1.0,
+        "factor": 64.0,
+        "mscale": 1.0,
+        "mscale_all_dim": 1.0,
+        "original_max_position_embeddings": 4096,
+        "type": "yarn"
+    },
+    "rope_theta": 50000.0,
+    "routed_scaling_factor": 2.827,
+    "scoring_func": "sigmoid",
+    "seq_aux": true,
+    "tie_word_embeddings": false,
+    "topk_group": 1,
+    "topk_method": "noaux_tc",
+    "transformers_version": "4.57.1",
+    "use_cache": true,
+    "v_head_dim": 128,
+    "vocab_size": 163840,
+    "quantization_config": {
+        "global_quant_config": {
+            "input_tensors": {
+                "dtype": "fp4",
+                "is_dynamic": true,
+                "qscheme": "per_group",
+                "ch_axis": -1,
+                "group_size": 32,
+                "symmetric": null,
+                "round_method": "half_even",
+                "scale_type": "float",
+                "scale_format": "e8m0",
+                "scale_calculation_mode": "even",
+                "mx_element_dtype": null,
+                "observer_cls": "PerBlockMXObserver",
+                "is_scale_quant": false
+            },
+            "output_tensors": null,
+            "weight": {
+                "dtype": "fp4",
+                "is_dynamic": false,
+                "qscheme": "per_group",
+                "ch_axis": -1,
+                "group_size": 32,
+                "symmetric": null,
+                "round_method": "half_even",
+                "scale_type": "float",
+                "scale_format": "e8m0",
+                "scale_calculation_mode": "even",
+                "mx_element_dtype": null,
+                "observer_cls": "PerBlockMXObserver",
+                "is_scale_quant": false
+            },
+            "bias": null,
+            "target_device": null
+        },
+        "exclude": [
+            "*self_attn*",
+            "*mlp.gate",
+            "*lm_head",
+            "*mlp.gate_proj",
+            "*mlp.up_proj",
+            "*mlp.down_proj",
+            "*shared_experts*"
+        ],
+        "algo_config": null,
+        "softmax_quant_spec": null,
+        "quant_method": "quark",
+        "layer_type_quant_config": {},
+        "layer_quant_config": {},
+        "kv_cache_quant_config": {},
+        "kv_cache_post_rope": false,
+        "quant_mode": "eager_mode",
+        "version": "0.12+15553c6a61",
+        "export": {
+            "kv_cache_group": [],
+            "min_kv_scale": 0.0,
+            "pack_method": "reorder",
+            "weight_format": "real_quantized",
+            "weight_merge_groups": null
+        }
+    }
+}

configuration_deepseek.py

@@ -0,0 +1,212 @@
+# Copy from https://huggingface.co/deepseek-ai/DeepSeek-V3/blob/main/configuration_deepseek.py
+
+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 +1,5 @@
+{
+  "eos_token_id": 163586,
+  "max_length": 262144,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:850570a86b7d0ece80d8da9dc11625b74d4882d1ffbe5ea217107f02c662878e
+size 3842424328

model-00002-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba2a1db2884156b229f4be2fd634157016701fd155485c9d9be9f9c05f35016
+size 1037270872

model-00003-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9e02b3bc140838988a30c57700fd6a8e4d3af10f0b54f85782fd7313411218
+size 1029471848

model-00004-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f916e615db04fd697402af1dd4418b234324c83461ac34a29f8081d115035c7
+size 1037271144

model-00005-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9336f4a0f98598f64a108267c7243854b1ebb58797708b5a9e1d9af5d27694d7
+size 1029472104

model-00006-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e04bcfcf7d7f417830aad23aed8811d9be8b26915c77d22e4ae62064c096daa0
+size 1037271136

model-00007-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ea7ec64eb4e57ad8e3c5192ed7c0436938e12a956e9415d0c7185904190fd8
+size 1029472104

model-00008-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5ffbf80008db5b41a3c92f9aed655fc57ae9da3f728fbde3b79a0ef0dc9521
+size 1037271136

model-00009-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a81d962f303e40797b74c1954dcae5fcd21bf9f3234137ad62702ca89939fe8
+size 1029472104

model-00010-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a208ad3704aa08ae37e05ff7ed30db7feca9f5f939a3ad5e7cd9f018b3074f99
+size 1270743528

model-00011-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4c6153334e92c785037f5c8ee3749e6e3e132c1b7da345f0949203d3345a66
+size 1037270872

model-00012-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:016e014950d22ba0a84528580e9b9f543150bb7342cdfb9fdb9e5b1102470847
+size 1029471912

model-00013-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfcb548638fdc46be3a7350ca8c8667257acb92a48510c493a268b8284e76ad0
+size 1037271144

model-00014-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3042606ad0192df4a415576320e2f435a4e9cf470bbb06137815018796ca07aa
+size 1029472104

model-00015-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dce402f65b8e8dc53e76d91df5323314a8c8e28731a7afc9bf9e815b8969421
+size 1037271136

model-00016-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c25b9911c244e6d12b2a2d5ba72b1eb97fefc046eacfae5905369e02405f8095
+size 1029472104

model-00017-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52dfba665aca3e48c63b8e03bdf012e742d0e28705921fae209e000e6c657df2
+size 1037271136

model-00018-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80927ced1ab0e0d19253c287e6b8c4f04a30b678c28cf87ef615297d59d070d9
+size 1029472104

model-00019-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb05f728dc85eb0ecc80a241b84e3a48dffb3fb8246e9b7c822a1f7c2c55f49b
+size 1270743456

model-00020-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a06415dc9be59d369f4a2fd4f841dde0a61ef47964963d89c9e051f945435728
+size 1037270872

model-00021-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a964adf3788006be215abf822c930a3fe95fcd8253ad8b83564d8e55f4c5e7d
+size 1029471976

model-00022-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85c259b0bd16602b46f517fd8e1bbaa5ae2850caef9262539280bb688738f02d
+size 1037271144

model-00023-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7105b387465987e5ff11643c56e9312b9987bc2c4258388c8264219462dde441
+size 1029472104

model-00024-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef4ceda5b42888b5b9e10dae32aea0b0b4e7af74b2d69f74c3ceb67816c6a24
+size 1037271136

model-00025-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1e286c7f742b7bd74cc24da0fe39865e64a07382e89c32d4ab91d331f6f2a2
+size 1029472104

model-00026-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3831ab8169f0bdf87dafbd7e59d96699a4da11e4bd85366f79b021125adaf2b
+size 1037271136

model-00027-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3270c2d8ff5af3d6d561d6b771307c0f25e831581d294cfd32f3ed0199acd3e7
+size 1270743704

model-00028-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9d76ac27f5d4fc1f523301af7fdb3ada27255fbf1c1fb2ab22a8a9fda6f7b7
+size 1029471792

model-00029-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29603543e4ed4aefe6376b8777577ed31b88d5eab45d6f2d44000fd2cff229c9
+size 1037270872

model-00030-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a4f736a297178cf3c0db71d22850980cc1214c90d4bad972fb7c2ca3125773
+size 1029472040

model-00031-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a85e85c8956810d10544bff0749794a5977bd25ce3cc861cde6b9b7d4fec8fbb
+size 1037271144

model-00032-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d63ef497a3fa09d78e12d3379b8d52f577171074fc0de4183fce45069de5282
+size 1029472104

model-00033-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7d0063c61429aafa80695e20acb4a5bad7028385b2203ad78dab42d4b1aad6
+size 1037271136

model-00034-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c7af6acd80e16c6f145ceec64310f5ec10ac653663a29e11ae58879e82f227
+size 1029472104

model-00035-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5a549b6f97e7645c6348723c2842472aeba24b0b9244732884e295b83db343
+size 1037271136

model-00036-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9887e107bf62c39a481dc8f968733ec3e60f72b3cccc372a3b1cf100bd9949c3
+size 1270743592

model-00037-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6a9855ff8a0611b3305a20d1541f856be411f7624b577380e44c3e8a777673
+size 1029471840

model-00038-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0cb774a21f0e8ff63e696ceaa31be6e52c678d0bd83cb7a13940adf668180e
+size 1037270880

model-00039-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c35c0342e163cbcd2c398c3fb972a8d2f8048848ceb5e8e84bb3032c7d5da60
+size 1029472104

model-00040-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb42a90b2a4ee620d0a2c34c79c43da13ce8db81c8a7ce6faaeda41a902783d4
+size 1037271144

model-00041-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2befa2ce1a6e14ffb258a2300f30860a39e24696ed546630e93e2485c1a291f4
+size 1029472104

model-00042-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f94e4466737248dee8d81641d97de8c64439e395a8eb09d3c1939eb3f4b3883
+size 1037271136

model-00043-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc757ded4620fbbc8712f2e10f8ade2bf057874e07a27b8b143c17a7ccb042db
+size 1029472104

model-00044-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6d1c442479437e5a78d124cf1f08fb1d0f8950639d18fc658132b1a76afe18
+size 1037271136

model-00045-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85fd29373779cf6b15b8b98d3d8a8427b82b33fb49bb03915f631a9d1d11a2c8
+size 1270743528

model-00046-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ce9cfddf5bdc81119f6613e3d05841d69079bf600d5c04f599e8b9d6fc660f
+size 1029471840