Upload folder using huggingface_hub

.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

@@ -12,27 +12,27 @@
   "aux_loss_alpha": 0.001,
   "bos_token_id": 163584,
   "eos_token_id": 163585,
-  "first_k_dense_replace": 0,
+  "first_k_dense_replace": 1,
   "hidden_act": "silu",
-  "hidden_size": 1408,
+  "hidden_size": 7168,
   "initializer_range": 0.02,
-  "intermediate_size": 9216,
+  "intermediate_size": 18432,
   "kv_lora_rank": 512,
-  "max_position_embeddings": 163840,
+  "max_position_embeddings": 131072,
   "model_type": "kimi_k2",
-  "moe_intermediate_size": 640,
+  "moe_intermediate_size": 2048,
   "moe_layer_freq": 1,
   "n_group": 1,
-  "n_routed_experts": 64,
+  "n_routed_experts": 384,
   "n_shared_experts": 1,
   "norm_topk_prob": true,
-  "num_attention_heads": 18,
+  "num_attention_heads": 64,
   "num_experts_per_tok": 8,
-  "num_hidden_layers": 18,
-  "num_key_value_heads": 18,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 64,
   "num_nextn_predict_layers": 0,
   "pretraining_tp": 1,
-  "q_lora_rank": null,
+  "q_lora_rank": 1536,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
   "quantization_config": {
@@ -46,7 +46,16 @@
   },
   "rms_norm_eps": 1e-06,
   "rope_theta": 50000.0,
-  "routed_scaling_factor": 2.446,
+  "routed_scaling_factor": 2.827,
+  "rope_scaling": {
+    "beta_fast": 1.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
   "scoring_func": "sigmoid",
   "seq_aux": true,
   "tie_word_embeddings": false,
@@ -56,6 +65,5 @@
   "transformers_version": "4.48.3",
   "use_cache": true,
   "v_head_dim": 128,
-  "vocab_size": 163840,
-  "rope_scaling": null
+  "vocab_size": 163840
 }

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 +1,4 @@
+{
+  "max_length": 131072,
+  "eos_token_id": 163585
+}

latest_checkpointed_iteration.txt

@@ -0,0 +1 @@
+517

model-1-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6588a247fcf5538b0fdcfeea096893e8b7dd9c5b060f732c64a9c8e4513642d9
+size 2846451040

model-1-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66929949e38022253b91face3fc5aa06b157d6c546bc464013ed268e561353f
+size 497640784

model-10-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a1acc308054a60d93c09064542a8234d077ed404da111e23e00a7dd477311d
+size 17066593104

model-10-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7088a10a61ce403feae24d019062427e13009c0fb030a719940865228e2a408
+size 17066593248

model-11-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d7bb19290aa16be216ed59d616d1ef8c837dfc31e73ea81860ae0c17b6bc066
+size 17066595432

model-11-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2679ca189fbf496682b086b918caa497ce4d0485c385efa7816d61ef12f9a1
+size 17066595576

model-12-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b6c4432d6562db0c22405ecfba1d9b5e8c7e52f63a53f223f379d516201678c
+size 17066595432

model-12-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe000201a5a7d7e9a46d9a17123991b84e72b14e64a80e8e78a646c5396ee2cd
+size 17066595576

model-13-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a53278f0777055cf4cf3f5e9daad803cf6895dd126f544880d3093c3c25be2ec
+size 17066595432

model-13-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8a15b9848c8d28eaa45726ccbd6b61ea6a050795f84c8ace58d6665691d4d3f
+size 17066595576

model-14-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260ce11bc3e2ff1ab14a610ef3eb77537c1f38ac3674c4e3921f19495af7ac58
+size 17066595432

model-14-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595d0048b97e3e537b6de012da09c8decd2a52868107c725ff59cf61d9b96adb
+size 17066595576

model-15-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f032c15758f09958ebac92eda24a68bd029e8db3e9f877864b36611d76187ea6
+size 17066595432

model-15-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec32f06f8befe4bec244a1639fba8f6d36d0caa0466b3b9acd1dd76d1db4b1b2
+size 17066595576

model-16-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a277ec201afc53edda1c109cae0f927a6c5ed25a5c8efb30556ed3f1c43c478
+size 17066595432

model-16-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557b2132770c324eae73e47f1beeac95962358ec11c81d1d49045fa31f7ef3b9
+size 17066595576

model-17-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b8f09959653888b434fbd7ecb0e4abb11f8be7fa222386733a57b567e69d4c
+size 17066595432

model-17-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43cd060ebe95fb6b42b4f99dc3880a37f33024cf8ab257ef5cd3a04c05c33da6
+size 17066595576

model-18-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1633da1551f0f6cd8948ef8e43be92fe94f660876570d8ba1ebf06320439f4
+size 17066595432

model-18-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb03d5693efa319dea1261aa0670252614154ae9a60b9b2027b0a9e8af989e2
+size 17066595576

model-19-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f0a7d395f0e8e9cbe3150a315a9f199222c19feae870f002610856c605a12a
+size 17066595432

model-19-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:144e1a30a9f46ebe0e33d9edf39a19db4be82b2664b87f5dada02003cf42624a
+size 17066595576

model-2-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b30915b84c270ce710df51981156d8b3f75a091df21238fcc7815c3ec88a61
+size 17066593104

model-2-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2055a533cf23eee917a58846f68575860560058a3f07e17b5cb181d598b83c98
+size 17066593248

model-20-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:847d034c34f5c9e4ad173b8808b43eb771b9359b20c286d49d892d621e88608c
+size 17066595432

model-20-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae77b383a177fd9f34d939e2fd9e26ee7856055cbf15871df0e099dfdedbbb0
+size 17066595576

model-21-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2e432244d1dfbe7e6ad290ddd0f0fc3b499978342b691e6545db6f6c1984a04
+size 17066595432

model-21-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea7434751a77c5ed9b4edb23e9cdbf8b146d8db56fe0934197522dfe7bf7387
+size 17066595576

model-22-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4212dcf0872a741ac89c1df73d26278a85393b85649029608a47ffb689bfbff
+size 17066595432

model-22-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd21a14846bbddebc1accc6757cd5190320249e7d1217e77bc5d91b44e09e4e
+size 17066595576

model-23-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba7127d0d6b8a4846eedf2d79af2f99ec017ed4ab73d9050f90789cce927418
+size 17066595432

model-23-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f86ff3f901e65e6190638bdd53f4854e394e2d0d3bb9da3cd97734ae060bf2
+size 17066595576

model-24-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47dda5474725ca5ec02aa6ccfbfd742319761ed6be04151aa23efb7498b46a17
+size 17066595432

model-24-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57865459c0a6dec1a78b7f7bfd297de8ddaa355bc85a711a69dad1790166a550
+size 17066595576

model-25-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8043e47252b37cbded4997128fd82501ebe13b55ce1b0156e8f0dc82934000c0
+size 17066595432

model-25-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4c026fbf85f13ef613374431d2caeea95b2b4f210113ec9ef3fda4e635d9c2
+size 17066595576

model-26-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7c266b4f2c2fb89d08148c0523d5ba59971ae5806587943f217064ee87dc1b
+size 17066595432

model-26-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba8714628aaa8980b633aaeaa9189358aa64d165539d1e211ac645fb1eed508
+size 17066595576

model-27-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4959b33787160976972c53e5b4849170e1d9bd194bab1b13f8542c21defbef93
+size 17066595432

model-27-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b745fab718f3e6c097294ac7ad9811db4c00b33cf5a1a76449a9257d6a92672
+size 17066595576

model-28-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4110af78af032ce3ebe8baae28f20dbdf455092cf35220a34cecc213d5ca0adf
+size 17066595432

model-28-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b4ed412797c87a1419350be495118590483a225f0e26ae50136d711bc709c6
+size 17066595576

model-29-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d261aaa72fc71696b20af14c5ab1d36263532030f91d20c5951c33b5f0819147
+size 17066595432

model-29-of-63.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d8a04aef1e2e1a2c56e15b5314fc28bc19c7e6d7fe5e33baf37ad2664d5d3a
+size 17066595576

model-3-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddcd18f3ec7ebf67ae168a6a0ba4cd1eb35f836c8f11bdfac2a1aa62ad45c590
+size 17066593104