DeepSeek-R1 W4AFP8

.gitattributes

@@ -33,3 +33,74 @@ 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-00062-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00034-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00054-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00033-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00036-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00039-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00041-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00043-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00045-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00015-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00018-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00050-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00053-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00022-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00057-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00014-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00058-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00009-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00049-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00047-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00027-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00048-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00055-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00069-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00017-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00038-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00046-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00070-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00028-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00037-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00013-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00031-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00025-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00020-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00024-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00026-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00030-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00061-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00011-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00016-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00042-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00067-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00010-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00029-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00044-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00051-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00059-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00012-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00056-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00066-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00032-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00035-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00052-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00060-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00064-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00065-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00021-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00040-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00063-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00068-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00019-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00023-of-00070.safetensors filter=lfs diff=lfs merge=lfs -text
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,61 @@
+{
+  "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": "4.46.3",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

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,
+  "eos_token_id": 1,
+  "do_sample": true,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.39.3"
+}

hf_quant_config.json

@@ -0,0 +1,6 @@
+{
+    "quantization": {
+        "quant_algo": "MIXED_PRECISION",
+        "kv_cache_quant_algo": null
+    }
+}

model-00001-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b42db19a504026648da4b1b8500ee2bfc8aeea8441f180c965fe5f058483676
+size 5375122560

model-00002-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b75befc14c66df3798392064f6180875fb0a900d99c90ea970455cfe933420
+size 5374473296

model-00003-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab96fd58712d1daee8192a091ae429af9e1cbeebd76e54f4e9d4b03b645c820
+size 5373515312

model-00004-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3325b75519fc8c9047ce95468f10bba81936e81ab9d5ecdddd1cf119ec37341
+size 5374493632

model-00005-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e223043bc7216865d5165c1bf52782e77ff4575e5894aacc3b6462d43bd2638
+size 5374473080

model-00006-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c65550538c86af0ffb9eb39b971eae84c6239734bf908c414fba7ef7c9afb4
+size 5374473080

model-00007-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85c34881a41344ea393fbadb7c26cd87f3874e9d70e697bc87582fabc298843e
+size 5374473080

model-00008-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f6acb6b536bb215355e4d70c8bd1ec7f9feb52e6e73fda2aac7861c5bd69ae9
+size 5374473216

model-00009-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39cd82596458621ea958a41bc11b1879abd1e39a3f35e987bf1562279964910
+size 5374473544

model-00010-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93adc2af8db76ccc7186399cf6f524d03710ffbd49e0a667191d9ddc9a42ec51
+size 5374474672

model-00011-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61fc500a96af6397de88bdc4047efb592e53834b976f39c2f6250f2f8e96f60f
+size 5373537064

model-00012-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94222184de72d8ac0ed6d8d62206352b3330232eef77d268b46dcf27b80b5f4
+size 5374474416

model-00013-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd129c46a003122df3acf84083e73701172b8df6e1749519935091f603caaa10
+size 5374474424

model-00014-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4503c3102cbbb1fc80e98a24ee1380c26c2032349744bc3b13b0da6c0457bf
+size 5374474424

model-00015-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:792a56918829b5fd0bee31baa860c2372aab77274b3820f6bf6d7e13d322a8df
+size 5374474488

model-00016-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288676ca5b3f885aea72e3a0d78666f7c6b67a572cb1d4cba34f12dedaa8df4e
+size 5374474640

model-00017-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade870e5a1134ca5ec43d3c57dc781f7ee0af840b2604af088d16cc913aeff01
+size 5374474640

model-00018-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b6eb11b0b538de73975a4ed729b54a1b90682d3f8c9501755ff2e2186319ce
+size 5373537160

model-00019-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e58ad0b4174aa39f6fdd0d723801a51578610b89481032f7aa2957bedfc1cf
+size 5374474424

model-00020-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658dbfd58a62a7e83acb4ab22dca86f6a7f625f9e9d097481c78ea7cf4a55ccf
+size 5374474424

model-00021-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d8840851e235455f28c0d96757521dafdbca9ade1e85ddbfb170178cacf0e3
+size 5374474416

model-00022-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a67749d430653adb1c81bfd28a138af73e5c48d7fd106374c28f87c8a3e210
+size 5374474424

model-00023-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd501d20b71120abc6b0c5e8bc152d72670c682af6e1ed41d38b753b1dc754f
+size 5374474632

model-00024-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a768b0182b09fb0f4590b53f83fc504d93ea660ca88901c4011d73cea433d2e9
+size 5374474640

model-00025-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61347e03a6da4a0c29770343af059ed7053a57808bdf64559e8ea48d3f0d591a
+size 5383794864

model-00026-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a60dd5163269d273a256012fae0021e9d9350dd879b8b26e85ecc587b10897b
+size 5372015832

model-00027-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d475513fc36d68b34ba172ff4a9ac2ae943668570792ed321c77a0f50bf4b7
+size 5374474424

model-00028-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394f41d9671217451fe8fc284e1a5bbcc4a58e28eba1ca16de8cac70c32edb03
+size 5374474416

model-00029-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d4fec8962fea815f11f18e61dc8303ef65c0964679fe65faf1d77610a70a440
+size 5374474424

model-00030-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9e4a428d1ae99fc39df2df4c01ccc874b4bfbbf578c7eada0d148b8c9c45e0
+size 5374474560

model-00031-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc9e619d086059c4eeb5894d8c61e2a2376221a265a14abbbea6006511358a49
+size 5374474640

model-00032-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f712e57e9a4a9ae3fe0243ac1c8d246a534d733a8c8c3171d371429b9379a6d
+size 5374474680

model-00033-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b337ab44ba4848bab371fa6b3703b3a0228d3ac251c72e2997fbdc54f72fb823
+size 5373537048

model-00034-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddfa61b0c1188188496f4f208b0055260c07b41082557218ede3e0aa81a6ee6f
+size 5374474416

model-00035-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79832b4a0951adddfd9b29d02431cf361d37bf728e7d3205f7b3573ce01ec97a
+size 5374474424

model-00036-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1804c51ea84e1aca3a2d43e88496b7d30f9490d39e39373e8f7f52a1bf81b3e1
+size 5374474424

model-00037-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e537324fa8eb5f4782d525e399acbd9049a5753dacfc00b522cd2961905b4a
+size 5374474488

model-00038-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6cf6e5771bd3fcd981bb164d06b8a6582a3a713d324bf5988f27e7dc44b9403
+size 5374474640

model-00039-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:385171ae4fa0c0eb7b6f1592bb6d704d0163711e3b01ce4de162e81d79e09f01
+size 5374474640

model-00040-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ebf024c5b03d965f4a5140953fe6f1316e16312864ba06767c10648b044bfe
+size 5373537160

model-00041-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e17a8c4a6ea36bfde2b2069556c9bc104c5a5317c61da5ffff645d0077e0fd
+size 5374474424

model-00042-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7411063c6f5e9d60629f51537ccddaecfa3721309b7ceb446cd969256e51ab
+size 5374474424

model-00043-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7199bdab9e55da270b610f35873c5b56c60a10d26e8c1cac4be1da5c27d230e9
+size 5374474416

model-00044-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06c9c59291f9944764a34118ec40aeeaa0bee276052a3cf77bb3d8cc1f6a5f1
+size 5374474424

model-00045-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b6bfd68f5f9b74ee934764eb6be15a6efe5011e341c9a02d810881c60962013
+size 5374474640