update

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163c125f6ca7659310b4bd67039891e38fa88189a6c0817871f977fc6ecf15d5
+size 1822

configuration_deepseek.py

@@ -0,0 +1,199 @@
+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.
+        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',
+        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,
+        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
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        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 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d08e384d8a46253bffea4c00dde0ceaf9a907b20ec221783fc26ca911120f34
+size 111

model-00001-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d52f9fa4f27104e210a89d6548ed8c08ed3e1da886446bbec0fa390f4e74e8
+size 4996018312

model-00002-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7bccd53c406f822ba760ec50e28ab15ffaa1fcb9f679af421babf03a158ba8
+size 4996908848

model-00003-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e67d7ab83ff97f50d84b938fc08a375079590d9aa0eb18cc2fadf56b5b3446
+size 4998414136

model-00004-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a69b5e6b7e2035d1d1e43d52c33a4231beedeb006d53de077fdb50d54093d1d
+size 4998383416

model-00005-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de3302ba5c28b733f2b1eb56fe4914f8704d13173f2d7680b6b6980e83213958
+size 4998414472

model-00006-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11b8f34e3b0f25824a1ed6457162fc9ee2b279e9a22d989470f894558f33b8f
+size 4998414864

model-00007-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c490be995a664f40be835a3fa7d044dc1820c62fb70d0cc66e2996c1b0857fb
+size 4996909120

model-00008-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37f75491d2f9c862b88d52be9a00ce919e73c87934664a157236e9a9fecc03c
+size 4998414136

model-00009-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0320987e47a0513b1d6bd2cb75d9c150671f1346711779bc7d9ffd023ee1559
+size 4998383416

model-00010-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16cc54eef74b0eade5b0f2e4d50510711e336e1810f0dccb20aa390ec398b576
+size 4998415664

model-00011-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c263225e00e6afc40a758a0fa61c0f5cfdda920079cb6dc3199e2fc669ed90d6
+size 4998418016

model-00012-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905ea15d0702415670532b6cfbf92205a86464d6526c5111e61fb75010a61175
+size 4975134888

model-00013-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd08aa633fc2c0ba809d113897866527b6ce2fdad9a562f7e5644fc9c2cebbb
+size 4996698472

model-00014-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92ce200d94f8781d79223040d37349a4027c2cc2c19952357a601d946eba649
+size 4998386576

model-00015-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44e2f9290eaf93bd212408aff9780fae0ea26350a10dc636bbb20caec143ee8
+size 4998417296

model-00016-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77fbe2c55ee8b0e0ccd75d2eb1e99c83e3db791981be9e113aec6775daa1079
+size 4998417824

model-00017-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b6d7fceaba4e4f61024ece36fcb655e474ea49855d92be3fd38c99da94d9dd
+size 4998387304

model-00018-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2a703d5dd77abe2c5647852a26b44d2fa911ab866887b1a7b1105499dca61f
+size 4996942824

model-00019-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc0cab91a06b2eb84563be7b3c0e41b2a1acb88fc6f6ec5303c467be64f55556
+size 4998386576

model-00020-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594a48343686e2fa3e90ebb306712b1643e90b7b4478c5347082be44e03cf8e1
+size 4998417296

model-00021-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6766f9cc29a002c25970f907b887967b87e8a2c7a8f2cafdf73056caac230788
+size 4998417560

model-00022-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4868183c46fd1b8224ec25575b95bae59625f87b97e5e3d19263388e9fc63270
+size 4998387304

model-00023-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e3c32cc7ebb989429f91b6ab5cfa9ba5dc1ec67bab4418632691da5f13c801c
+size 4996943096

model-00024-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80caee74bd265a2c0f8a3fb16494cad8ca5fc864f5659fd6232cb395ce9b0a9
+size 4998386576

model-00025-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d42d46228c96244b5ea5bc4ae98a5e0e70ec8d4076928a2ba21dc802a313d43
+size 4998417296

model-00026-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3938e893671011096d806f8d3463eef88bb40be644ffe7ea7bb6948a69cc94c
+size 4998417288

model-00027-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bcf1bb8eff67761c1472e8054f23e0153ed568698453402b8fbddc200f9d23e
+size 4998387304

model-00028-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031b75f8df42695568b38db841991144bef35da488cf7f3cb20668a4a27447a3
+size 4998418128

model-00029-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c926aac8abef2103981ad0513a836954d0207817251402ade7aecd65555427
+size 4996911808

model-00030-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6551bcddb70eee6a7994f5a88a3634525f80aaf8c40ccb3a45d9551ac95adbc8
+size 4998417296

model-00031-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc01ae1fefc6f614838fe3d81fecc905edf8c022b6565607668848802d9fe8b
+size 4998417288

model-00032-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:613e81a1629966b7b9fc7e708b6386645a79f83e17f1ba18583b5f5f97818794
+size 4998387032

model-00033-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c9f2d0d54017bd4cb3f8ceae6ecc1170df4529137a4e8171d5f73aa4f5c3f09
+size 4998418024

model-00034-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b557fe6269246a84e6f8df479b91709ecfbb99cc1eb2b9eca05410e5e536b09b
+size 4996912184

model-00035-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12af475cbc80faf46d4f4fe79665ae1d17e61ed1d4dce96b186175fb75337f0
+size 4998417296

model-00036-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842db74978f300116cc41676fee996fef5a018b701c0c93ddb3524ab6fe33df8
+size 4998417288

model-00037-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cdc323d6aebe998e3533a07b0d3efe7e38c646f1556fdbd48102bb0b008b7fc
+size 4998386760

model-00038-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e4dba0ce45f668aee0739646b5f4685e0ec18a976cc0b98027dc08c9bb2dba
+size 4998418024

model-00039-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563d0e143d0957a509b889909ff1392da3196aea059e621f97e66eee11ab3eb9
+size 4996912456

model-00040-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66faf9cb975b5c0a1e2a622998b474fc7261c9eb2bf35c4a505ab0fb3f236501
+size 4998417296

model-00041-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:989937026a7835c11a1de3eaf0c9a64f2deccabcec81948fcecedd437d3028c9
+size 4998417288

model-00042-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475136812a8dfbc82f7cbd324e1264188c2f126a8a6ab4485887004a982fc16d
+size 4998386576

model-00043-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b0b7fdaf61a21457be0ed878c6d8c25a461f2bf43cb239af6db0aa24415562
+size 4998417944

model-00044-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a90ef3c944807e61c975af52bbd714c6e14e1317a4e190df337630db05c07f8e
+size 4998418048

model-00045-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27dd7dc144b80aefbf4575a07aeb8d9ff92fb6831e53bf34355d2cc910b200c7
+size 4996911968

model-00046-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3861dfe2f6d4e538a8a60a6f9e4bde7b0f35379e85a83a84846d30dcf26e6d
+size 4998417288

model-00047-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:494c17f2c0a2447d026b23e4a37dd1c8739a55196354da2a3772ac31c5a4cf94
+size 4998386576