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 sha256:3f002ada3ed922e5b69217f51c926d3ecae9617a33877f072ae0f80a828159ec
+size 8594017186

model-00002-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499d087b9b3aa4154c195a89817ef92f4976fb34f7dfaee3652d60bcc4ba2a84
+size 8604902394

model-00003-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c194f3266e1f41d0d9603b2f4066b08d38faa9c2f27c3bac1b3d5c6d4df0e11
+size 8604902394

model-00004-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2b858f5475969f4dee95408c91b0266a2c7b181cfaa37c5f69381ae436e4de
+size 8604902402

model-00005-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16c7ff7d698462a2da776a08d1259185c82c0b1491a6169530ff81548f12238
+size 8590441833

model-00006-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1347953a60916ecda10247af18b5a2082533c3e3ef2211f5474a5eaeeff331fc
+size 8604902329

model-00007-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad694df073409acefa149c29b22ac8e319266e16904c163ba4569c2ecc5d4c6a
+size 8604902352

model-00008-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91bc3a38101b0728d2a5179c70e6801facd589d69a715d2cfb8f8de7c6c97ce9
+size 8604902352

model-00009-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded33082bda554106d01df53cb2d8dfe3e8d14440a99eb0d8088d80a90924d28
+size 8604902538

model-00010-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb3249d75f257c41de4a0e53894c3144781a055692621de1941780f8bb45656
+size 8604902887

model-00011-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b094910601b74c658c32d5c66d1ad666aeeaf229219faed09eab94887b9c27c4
+size 8604902887

model-00012-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8f6f98ca827cb637293e62612a533da8c50dd67842885082297e6d5566a907
+size 8604902888

model-00013-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ec5c369382ff1950d706c1afa5244fd887035745611657b5e0e7ea63bdca5a
+size 8604902929

model-00014-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b4d96cb2e9ac3d0af320d7eb5a1e8de12667d4a57d59f0dfffcdadd5fb6493
+size 8604902929

model-00015-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4fa3d7433c6f54a847bf3b461efd72f78954ea85c101297b58cbf350627b7c
+size 8604902929

model-00016-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf362034cf2e44e06e53566bd56244a63505c1a7e7cc9d85283ca6775b48046
+size 8604902933

model-00017-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e84fb0f5be339264e848d428d4a5c94d9f6afb4adbbf8c8bf214d14965b9734
+size 8590442357

model-00018-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092c61048ad2106d01bce1fb35c91ffb34ce0114c58bffa05ceb3e7366787447
+size 8604902862

model-00019-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc492030a3350ca8bd29383e43aa042110bc113b17437cbe1fd6c0603a4c0036
+size 8604902887

model-00020-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f066f34346b11680e51e6d56e5c3eaee12e0ee7f2e17495f24f6c766a49b79
+size 8604902887

model-00021-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a88a7ed3f52734190c12a88618194ee6142f18aa3c6d0663113342c0080b93
+size 8604902887

model-00022-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eabd44d56d8684b2fb1a73c95d151d32331d9f1619c2b32e4e9cb689435740b
+size 8604902887

model-00023-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02209963adb85a4842984b79538e1725638b73fc275de70255976137582588f2
+size 8604902887

model-00024-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b4a3b84905ed31026bff9d047c35c3e2a8714524caad6b62f504c2747efb09
+size 8604902887

model-00025-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebbf1992b4d006ac6bbeba4b9b53a6362e44e1099057908dca385969670951d0
+size 8604902928

model-00026-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb8c7e644962fdb552083aa9bb3d038ddfeb8b7b0b0213f22ef66de46944116
+size 8604902929

model-00027-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c23f4d882247d621eced94a42588dc76a03784ad84e47eb35d86bfbf2debd792
+size 8604902929

model-00028-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a42497735037e9504ba549455b4fdd51aac772eb75daabd149a75fbd9747039
+size 8604902929

model-00029-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ea5ded84274b784bdbb818fe38c480386ae20fe0bb26635ac5bf7fb789e591
+size 8590442363

model-00030-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f64101ed7475008eb8a63ae0a3dcae08589181a5d669c35f087da9f954cf0c3a
+size 8604902860

model-00031-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106f80ebca13dbf069ecf842274fdadb3c419f3db8af26971c74e8941b3eed3d
+size 8604902887

model-00032-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d0ae7cf3814551e7fcc4701b3d21ae03a5ff6925cfd39567d7b0c246a7211c
+size 8604902887

model-00033-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b13b658d7c416e31862385d9c33ffc35795e133059793dd9d7c436d628f48c
+size 8604902887

model-00034-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511916e5554c7434656902417bd1139041ddfaee838637ac153d790f3dad15c2
+size 8604902887

model-00035-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06dbf6282f3b923eaae34480462e2f06f311c19f67132646567d38ceb51127f6
+size 8604902887

model-00036-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1bfec1e685279abf151b58efbba59a1cd311a8305116d233eb3a7b912e0859
+size 8604902887

model-00037-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2033c195d50aaca5bfedaf9e7769322291b066cdcd84bdcadbb616b0f81b78ac
+size 8604902926

model-00038-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e30a48e242472205813ba8d0c3ec66176b26352db912f6fa24a875d1d08659
+size 8604902929

model-00039-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5c8bc575f7a7c860f476fd3ad69ac6757711e2ee3607d5d0ae53fc5427e81e
+size 8604902929

model-00040-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1d237183a70778d5879dd929548ffcea7a05a667bd48619f6bd4de92839aae
+size 8604902927

model-00041-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8a3f25fd18b9da195ab1ab6110450185c8f542039391b991e6cda570806532
+size 8590442367

model-00042-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf6aad12ab422b3559c2701c5d4992daae3183c61924fd5e194ed7f912f38b5
+size 8604902858

model-00043-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a42a80cd2acbcb2120695e1f5b777eaa2aade66cf7186592b1324e7ab08a66
+size 8604902887

model-00044-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32c41865b25033b0135a40eb20d11fe0029f72a9229eec23d71ccfb5222a4b9
+size 8604902887

model-00045-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7fff34ffd9ffdad793f7ea280984c4573d2198d55b23a05c922189de3af0cd9
+size 8604902887

model-00046-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:488a1db56a02b3faa4e7c95f0cb3bb610137d891c17d4d46cf6fd137cacf6517
+size 8604902887

model-00047-of-000055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230721a74f6354df045c1243eb3c8e64ab3d95def8819e546b90f4e13dc82c9b
+size 8604902887