Upload folder using huggingface_hub

config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "DeepseekForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekConfig",
+    "AutoModel": "modeling_deepseek.DeepseekModel",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek",
+  "moe_intermediate_size": 1536,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 160,
+  "n_shared_experts": 2,
+  "norm_topk_prob": false,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 128,
+  "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": 0.707,
+    "mscale_all_dim": 0.707,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 16.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 3,
+  "topk_method": "group_limited_greedy",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 102400
+}

configuration_deepseek.py

@@ -0,0 +1,206 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekModel`]. 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-7B.
+
+    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 102400):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekModel`]
+        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_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 DeepseekModel, DeepseekConfig
+
+    >>> # Initializing a Deepseek deepseek-7b style configuration
+    >>> configuration = DeepseekConfig()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=102400,
+        hidden_size=4096,
+        intermediate_size=11008,
+        moe_intermediate_size = 1407,
+        num_hidden_layers=30,
+        num_attention_heads=32,
+        num_key_value_heads=32,
+        n_shared_experts = None,
+        n_routed_experts = None,
+        ep_size = 1,
+        routed_scaling_factor = 1.0,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        topk_method = 'gready',
+        n_group = None,
+        topk_group = None,
+        num_experts_per_tok = None,
+        moe_layer_freq = 1,
+        first_k_dense_replace = 0,
+        norm_topk_prob = False,
+        scoring_func = 'softmax',
+        aux_loss_alpha = 0.001,
+        seq_aux = True,
+        hidden_act="silu",
+        max_position_embeddings=2048,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=100000,
+        eos_token_id=100001,
+        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_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": 100000,
+  "eos_token_id": 100001,
+  "do_sample": true,
+  "temperature": 0.3,
+  "top_p": 0.95,
+  "transformers_version": "4.39.3"
+}

model-00001-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5314c26dbbd06884bc3f9007ec444ee1c8ffa6d09666743dea44510e9f5263d7
+size 8594017192

model-00002-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00165998ae8e57fe6c206fbbe1f904c38f2a6d29ba58271417effcc110c0db1
+size 8604902384

model-00003-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b949f728b0e06cb90e41caa346eb0bf8410d30047fb0a58ae242027e07646d
+size 8604902384

model-00004-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307a89a55ae13751eaf284d6baa1069b770f0b1cf31504c117155955f22ecb88
+size 8604902384

model-00005-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ea2eda31e2958ede242f2b96e63041ec4c175763f4b21456208b5f15cee0c4
+size 8590441800

model-00006-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd13157910927a66408c00470d095373f0e41ab9d93b775f0aca17da6942300b
+size 8604902320

model-00007-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1584a31875340653d2b401ebf2ed2181b7ddb5cd8a1185123a311ccd37738e
+size 8604902344

model-00008-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861e6fb06e083540fabff7387c8561b05242b87c314966c3afd43d7f62640948
+size 8604902344

model-00009-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71563829a433bdc3377464fae9cf46f18933a18f9a4eedd270d7a26511ddce49
+size 8604902544

model-00010-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec4a98487776bbca4505aed9b552fe3cd84efd09eb0e6388168c459466af7ed
+size 8604902880

model-00011-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46baac5a84d58e8915875ad4c93a0d352187bd803ea129f8ac558d1bcf44f831
+size 8604902880

model-00012-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846fe99467bb01d5b427fd236aa4751857ebde399745becb16033b2b3fceed35
+size 8604902880

model-00013-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055e502dffc8dc05e3935f2703ac21d33dfcf095e037de07f491b48612478a34
+size 8604902920

model-00014-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7484344f8ae46f964a865a516320ea5dbe5864403d2cb497c2791823f864d6a
+size 8604902920

model-00015-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8782675a3d9616e8afdff9df1a2b14e1b5f8167136a0a894d4d74ab6ed4f81
+size 8604902920

model-00016-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ca0d9f9bb08e4f674d69031511195233ec6ed45e3530cd8bd8a493f3bf2b01b
+size 8604902920

model-00017-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0da315f46206e76f8e11d24883091ba148fabd5c599cfbf5a5281488c87d4c0
+size 8590442320

model-00018-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579ade2dce32f85cab7d7c57b665b4af1a52b2df120520cfb9c95b042e5db399
+size 8604902856

model-00019-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2723b1752fc4f76594803c181f69ab2713d2a426412139cd8fe18b7134b4f7
+size 8604902880

model-00020-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37a15c4558ace7e9f9ece427388dcd37f78f03d939139dcedf9139ad30a69f1
+size 8604902880

model-00021-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50543f021ca99f32ec6b8861ec9de8ef643e34db602cf99446fde004f053feda
+size 8604902880

model-00022-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fda43a9bf5fa595b20025e9d121fc60def5ea9b7d0b8c974708107d1595aef8
+size 8604902880

model-00023-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c2d09c017d71b604308376eb7419d14fb0bf8c4efc767e9dc1b621e56d04d2e
+size 8604902880

model-00024-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e013a38a3726a650c90133c3ab2dab49464722456d347645f3174a41beb9c63
+size 8604902880

model-00025-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344d1b64c3f840c9f764c5918ba2b3e35f393a07fd875725a5ab957c7f7bf897
+size 8604902920

model-00026-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f199bd563b912c294114bca8bc8a394176bf8f04b099bcb4862a773ab1713af
+size 8604902920

model-00027-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d48913ce4750b84abf25f8fec36f378abff2cb2d8f4d6f44a1745c2046236e
+size 8604902920

model-00028-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fc490839512b3766bc10c7b2df71c8467977a7799945f7d895d6dc522a0de8
+size 8604902920

model-00029-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced6740536f763872840a5fea01a0533c20c29e6ac2055d27d969a574d5a8a7a
+size 8590442328

model-00030-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61aa216d0983f0afcd529264fce8a657d34ca39cf836c6c73d4ab2c3149b0b45
+size 8604902856

model-00031-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ff28f5dcca515a464a2b7f84818284885c0badeaf5d5badbdfb9f16908cbed
+size 8604902880

model-00032-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a676b4fe5cbf60430b0a295b10fb4bd896d8578440f5e7652bfafba09dc7b89d
+size 8604902880

model-00033-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:517b2a363019942ee7c8a0de14547619180c83663290770e5b20fed88eb7ae9f
+size 8604902880

model-00034-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27077023a02166994ae9c7a4101f75dd90396c317b3d8a89e3c7a58c117cc66d
+size 8604902880

model-00035-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a88bac75d7c6fe543750500e6b41227cc3a0ee06399a961fcfe0eba068056dd5
+size 8604902880

model-00036-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f3fc5fd5e1ccaf3ccb808031c76d084e2d7ce5b23526d2a74c0be50e3fc3be
+size 8604902880

model-00037-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b71b86733f0a7971b0d76ee126734160ba69be651324488641e40119db1e007
+size 8604902920

model-00038-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6cd93c33cd36946f78d31bdde1f0e70c08fc9a433c3d52a7ac19a0c3031708
+size 8604902920

model-00039-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cdbba7951b1be016778ba6fe0093d6b6d2d2dc3c4cd803f1adefad67a530f93
+size 8604902920

model-00040-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34df161df65f09d4fca587d071c01b385a837e31a07e3ede24bef3eb4afec281
+size 8604902920

model-00041-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b62683d507c130f5fc72b713ef01c6c5df4380b662a7d5401de2f37520293f
+size 8590442336

model-00042-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a163490c0863da3e0135ef2d7ef4194a12e0a98edece424d344f2e1fb60d41
+size 8604902848

model-00043-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314a221c74d256635114161eb600e7d50700bf7791fcc8ca1118257ae0aac696
+size 8604902880

model-00044-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f49b57a7d0dac8ae7b94e210c5c01eb7aaf665a49469e8e08395cfc3464ae43
+size 8604902880

model-00045-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b879e881461afa9f0de10cd0330414a448dc6729b90eee1f9e51198ea0d6dfb
+size 8604902880

model-00046-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b049c90c79a7b27669595ca489a2abda0233d1152b735633ad135332d9e2e3b0
+size 8604902880

model-00047-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5649139ad4cc2fb3b6cc32f919d716efa37d7221b9eec15537eb72eb2693350f
+size 8604902880