appended original files

chat_template.jinja

@@ -0,0 +1,37 @@
+{% if tools -%}
+    {{ '<|im_system|>tool_declare<|im_middle|>' -}}
+    {{- tools | tojson -}}
+    {{ '<|im_end|>' -}}
+{%- endif -%}
+
+{%- for message in messages -%}
+  {%- if loop.first and messages[0]['role'] != 'system' -%}
+    {{ '<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>' }}
+  {%- endif -%}
+  {%- if message['role'] == 'system' -%}
+    {{ '<|im_system|>system<|im_middle|>' }}
+  {%- elif message['role'] == 'user' -%}
+    {{ '<|im_user|>user<|im_middle|>' }}
+  {%- elif message['role'] == 'assistant' -%}
+    {{ '<|im_assistant|>assistant<|im_middle|>' }}
+  {%- elif message['role'] == 'tool' -%}
+    {{ '<|im_system|>tool<|im_middle|>' }}
+  {%- endif -%}
+
+  {%- if message['content'] is string -%}
+    {{- message['content'] + '<|im_end|>' -}}
+  {%- else -%}
+    {%- for content in message['content'] -%}
+      {%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}
+        {{ '<|media_start|>image<|media_content|><|media_pad|><|media_end|>' }}
+      {%- else -%}
+        {{ content['text'] }}
+      {%- endif -%}
+    {%- endfor -%}
+    {{ '<|im_end|>' }}
+  {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+  {{ '<|im_assistant|>assistant<|im_middle|>' }}
+{%- endif -%}

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": 163586
+}

model-1-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:548406492f92989b7568759c3e08814a863d776ecf668a24c18eaf7e771ec8bd
+size 2774043272

model-10-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07c6fc0b8c2a68f2900f68e127901105aee2908eb89c3411399ddf1d16ec385
+size 9745794840

model-11-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ecdad68243c45a1d7a6013a87c19fc527a54c0e8361308fdf683373555582e
+size 9745799472

model-12-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:032306fe151190f589d71a7e82d7fa38b470d5c5c0e66abe56f4344ca83dd51b
+size 9745799472

model-13-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85dd0cb6b46fd124263f572977fbdb9b6adb56bbe97556b43cffb3d7f21df61c
+size 9745799472

model-14-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8705b6ff68f838ae4523e1bb0629881c9b2aa267bf18238fa70d52af702ca20
+size 9745799472

model-15-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13f81aad07269e3c5d3c8c10015152bd542afbcd92a0451fe4720f38ddec3197
+size 9745799472

model-16-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11608558334f11fd13a51b8e3779e5de2f2fbce26b08155318416847663a06da
+size 9745799472

model-17-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6687ab08ce71db3c295989b61f33bc2d59fa4ddc2b90b76a22336e3834b95f34
+size 9745799472

model-18-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e4b6c9f4f55582dbfaaa1f9da5acbc08b9931b22c1434e0bb5e01c3c5afe20b
+size 9745799472

model-19-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e43e7fbef8aa2c379d0fb6825d2cd480faf6284d268aecd33d5df71abfd36c
+size 9745799472

model-2-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a515b8130f35ac459d8fd19fc5418dd997cfe34fe9d06e65ad9d4698a5336dd9
+size 9745794840

model-20-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6991b62e82faaf138f0bde9af1565fac3b7e76f86ae4afe0cace70a4213a3541
+size 9745799472

model-21-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d95ecbb159ca4727af407b14ab6e1fe60b11b29e1b7b057fd539a7de34f8e954
+size 9745799472

model-22-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf88702a615c8d8401d1d79655bd087b9e686f7ca19d6afd354803f2ce4c5786
+size 9745799472

model-23-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f52397f64034afc3068b8c8aefd1b2f6f6820df869d494372aa8815d70a345
+size 9745799472

model-24-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688cdf04eba63de915620d6cfbcada6792badc70d8c6e3c0597532e97af2da2a
+size 9745799472

model-25-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b091f65ca516b1845b7dfcd52957213a6dee575fbd65f1087ebd4327ac334e
+size 9745799472

model-26-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09fa8c8963cbd58dd3d266d3470e49cc416a2980e4c71fc5075c5d551ba3caea
+size 9745799472

model-27-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8add19ac44aec7e2b1c10e6d108b207176ee1900a08c52a0fbda30daf27e6254
+size 9745799472

model-28-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da8c02433c5d1eb7ef96f2c6b29901be0ee0cb0001d2c10bd64921380107fb5
+size 9745799472

model-29-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34512e203463946e01f934c0c285ebeaa79ba8a2324e8d46e2721d1a98ef002
+size 9745799472

model-3-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6588df8dd8aa961bbd0a030c0b2174cbd6831c88891f4bc9b436c98455b07399
+size 9745794840

model-30-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab0e818fa5b128894f4f0d18c674edf0baf84d086000bb7df0df85c5e4b8108
+size 9745799472

model-31-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd6d5ce4f6e9841dc13341f6ea8ef214e6143cf7924930a69dfcf7e052693d6
+size 9745799472

model-32-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05fc116fe731bce09389c3ba6f412aa92e5d58f14c22dc418fde79608d59baf1
+size 9745799472

model-33-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33ac6d5871155e598d40713ab05ff9bdeec2802ba7ebff96cb020bfeccb6b423
+size 9745799472

model-34-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf6b3b376ae3c3726499fb130eda82c32806a53a39d8116ccba7913898eeab2
+size 9745799472

model-35-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b280dc5a7abbcffc89f9ab27ce97a6b6887ea423c15038ba7d3b6c19ead108
+size 9745799472

model-36-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89cf693ff0c014a37cebae6a8cdea12025d18b8a08984e36ec4000608db0ff30
+size 9745799472

model-37-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdbe37d1d081e6cd228de2d56d9d1ca793df972633f031dcb138e21328d12784
+size 9745799472

model-38-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc5c0f7e9a63f53e9cf03419b63d4ba1faaa9df7c90595a78ec27dbc7a8e1a99
+size 9745799472

model-39-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1842042e500b4db14624e1761dfc0a678df0959434c9023232796db4e5275ead
+size 9745799472

model-4-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c77c07cb4ad8e574d72b58585e28a2a9442635c7a0dc6c15397b50c3732d038
+size 9745794840

model-40-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6229be52e4ab6dd94ad733213029f6413794f47c03fcb2b4352118c3a58d32f5
+size 9745799472

model-41-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d3638f38d2f5afaba671bd847d9b5165fe67375b4628174b2ebfe3f635ceb0
+size 9745799472

model-42-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b5ba66abb2977264f45ad436069c5641eed38c1536929ec9204cc2c66f3d9d
+size 9745799472

model-43-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f79b85c1e00509a704b8b737178cf1b05a727e30f86f7ad61ace9ec923727dc
+size 9745799472

model-44-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0319bccd18d5b71dfcb3839b855b0fcc9ef21c36ddf06cbe36f8ff0e0c62515
+size 9745799472

model-45-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec271b3c3413155e98ada6936c8fcc693e1ab59bb382a09bf3299c490307a96f
+size 9745799472

model-46-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b859ab174c86d39ae1739f70a22ea598eb68b27f1dddfa4cb85b7676f6cc8ca1
+size 9745799472

model-47-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c8107cf8819785f5d873073468e73877abcf50a20f670fd64102235c3682002
+size 9745799472

model-48-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9495244a193560df082d0f3a0e1f2863495bd2ad203fa4ab7aba4b525698221f
+size 9745799472

model-49-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba179d78da55d5df8dcafaf7ec8f875746daaf85148e403fdcb0e803010b1aa
+size 9745799472

model-5-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dba5657cc7ae76d4e13bb5f51386cba389e4bb73918f9718ffce676a347bd63
+size 9745794840

model-50-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcf2e1a3c66ee8fc5e7a98db5abe4dc72eeecc37dac8cefe7387db2e43ab1914
+size 9745799472

model-51-of-61.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0eb0444361f6aa3bf2f15dec48154757648e2ba403dbbf9fc8715f960de4e6f
+size 9745799472