xinference 1.4.0__py3-none-any.whl → 1.4.1__py3-none-any.whl

xinference/thirdparty/deepseek_vl2/models/configuration_deepseek.py

@@ -0,0 +1,210 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV2Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV2Model`]. 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-V2 with multi-latent attention.
+
+    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 [`DeepseekV2Model`]
+        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.
+        use_mla (`bool`, *optional*, defaults to `True`): Use multi-latent attention or multi-head attention. If True,
+            the model will use multi-latent attention, otherwise, it will use multi-head attention.
+
+    ```python
+    >>> from transformers import DeepseekV2Model, DeepseekV2Config
+
+    >>> # Initializing a Deepseek-V2 style configuration
+    >>> configuration = DeepseekV2Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v2"
+    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,
+        use_mla=True,
+        **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 = float(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
+        self.use_mla = use_mla
+
+        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,
+        )

xinference/thirdparty/deepseek_vl2/models/conversation.py

@@ -0,0 +1,310 @@
+"""
+From https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py
+"""
+
+import dataclasses
+from enum import IntEnum, auto
+from typing import Any, Dict, List
+
+
+class SeparatorStyle(IntEnum):
+    """Separator styles."""
+
+    DeepSeek = auto()
+    DeepSeekV2 = auto()
+    PLAIN = auto()
+    ALIGNMENT = auto()
+
+
+@dataclasses.dataclass
+class Conversation:
+    """A class that manages prompt templates and keeps all conversation history."""
+
+    # The name of this template
+    name: str
+    # The template of the system prompt
+    system_template: str = "{system_message}"
+    # The system message
+    system_message: str = ""
+    # The names of two roles
+    roles: List[str] = (("USER", "ASSISTANT"),)
+    # All messages. Each item is (role, message).
+    messages: List[List[str]] = ()
+    # The number of few shot examples
+    offset: int = 0
+    # The separator style and configurations
+    sep_style: SeparatorStyle = SeparatorStyle.DeepSeek
+    sep: str = "\n"
+    sep2: str = None
+    # Stop criteria (the default one is EOS token)
+    stop_str: str = None
+    # Stops generation if meeting any token in this list
+    stop_token_ids: List[int] = None
+
+    def get_prompt(self) -> str:
+        """Get the prompt for generation."""
+        system_prompt = self.system_template.format(system_message=self.system_message)
+        if self.sep_style == SeparatorStyle.DeepSeek:
+            seps = [self.sep, self.sep2]
+            if system_prompt == "" or system_prompt is None:
+                ret = ""
+            else:
+                ret = system_prompt + seps[0]
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    ret += role + ": " + message + seps[i % 2]
+                else:
+                    ret += role + ":"
+            return ret
+        elif self.sep_style == SeparatorStyle.DeepSeekV2:
+            seps = [self.sep, self.sep2]
+            if system_prompt == "" or system_prompt is None:
+                ret = ""
+            else:
+                ret = system_prompt + seps[0]
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    if role == "User":
+                        ret += "<｜sft▁begin｜>\n" + message + self.sep #<｜sft▁begin｜>User Input<｜sft▁end｜>\nResponse<｜end▁of▁sentence｜>
+                    else:
+                        ret += message + self.sep2
+                else:
+                    ret = ret
+            return ret
+
+        elif self.sep_style == SeparatorStyle.PLAIN:
+            seps = [self.sep, self.sep2]
+            ret = ""
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    if type(message) is tuple:
+                        message, _, _ = message
+                    if i % 2 == 0:
+                        ret += message + seps[i % 2]
+                    else:
+                        ret += message + seps[i % 2]
+                else:
+                    ret += ""
+            return ret
+        elif self.sep_style == SeparatorStyle.ALIGNMENT:
+            seps = [self.sep, self.sep2]
+            ret = ""
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    if type(message) is tuple:
+                        message, _, _ = message
+                    if i % 2 == 0:
+                        ret += '<image>\n' + seps[i % 2]
+                    else:
+                        ret += message + seps[i % 2]
+                else:
+                    ret += ""
+            return ret
+        else:
+            raise ValueError(f"Invalid style: {self.sep_style}")
+
+    def set_system_message(self, system_message: str):
+        """Set the system message."""
+        self.system_message = system_message
+
+    def append_message(self, role: str, message: str):
+        """Append a new message."""
+        self.messages.append([role, message])
+
+    def update_last_message(self, message: str):
+        """Update the last output.
+
+        The last message is typically set to be None when constructing the prompt,
+        so we need to update it in-place after getting the response from a model.
+        """
+        self.messages[-1][1] = message
+
+    def reset_message(self):
+        """Reset a new message."""
+        self.messages = []
+
+    def to_gradio_chatbot(self):
+        """Convert the conversation to gradio chatbot format."""
+        ret = []
+        for i, (role, msg) in enumerate(self.messages[self.offset :]):
+            if i % 2 == 0:
+                ret.append([msg, None])
+            else:
+                ret[-1][-1] = msg
+        return ret
+
+    def to_openai_api_messages(self):
+        """Convert the conversation to OpenAI chat completion format."""
+        system_prompt = self.system_template.format(system_message=self.system_message)
+        ret = [{"role": "system", "content": system_prompt}]
+
+        for i, (_, msg) in enumerate(self.messages[self.offset :]):
+            if i % 2 == 0:
+                ret.append({"role": "user", "content": msg})
+            else:
+                if msg is not None:
+                    ret.append({"role": "assistant", "content": msg})
+        return ret
+
+    def copy(self):
+        return Conversation(
+            name=self.name,
+            system_template=self.system_template,
+            system_message=self.system_message,
+            roles=self.roles,
+            messages=[[x, y] for x, y in self.messages],
+            offset=self.offset,
+            sep_style=self.sep_style,
+            sep=self.sep,
+            sep2=self.sep2,
+            stop_str=self.stop_str,
+            stop_token_ids=self.stop_token_ids,
+        )
+
+    def dict(self):
+        return {
+            "template_name": self.name,
+            "system_message": self.system_message,
+            "roles": self.roles,
+            "messages": self.messages,
+            "offset": self.offset,
+        }
+
+
+# A global registry for all conversation templates
+conv_templates: Dict[str, Conversation] = {}
+
+
+def register_conv_template(template: Conversation, override: bool = False):
+    """Register a new conversation template."""
+    if not override:
+        assert template.name not in conv_templates, f"{template.name} has been registered."
+
+    conv_templates[template.name] = template
+
+
+def get_conv_template(name: str) -> Conversation:
+    """Get a conversation template."""
+    return conv_templates[name].copy()
+
+
+# register_conv_template(
+#     Conversation(
+#         name="deepseek",
+#         system_template="{system_message}",
+#         # system_message="You are a helpful assistant. Please answer truthfully and write out your "
+#         # "thinking step by step to be sure you get the right answer.",
+#         system_message="",
+#         roles=("User", "Assistant"),
+#         messages=(),
+#         offset=0,
+#         sep_style=SeparatorStyle.DeepSeek,
+#         sep="\n\n",
+#         sep2="<｜end▁of▁sentence｜>",
+#         stop_token_ids=[100001],
+#         stop_str=["User:", "<｜end▁of▁sentence｜>"]
+#     )
+# )
+register_conv_template(
+    Conversation(
+        name="deepseek",
+        system_template="{system_message}",
+        # system_message="You are a helpful assistant. Please answer truthfully and write out your "
+        # "thinking step by step to be sure you get the right answer.",
+        system_message="",
+        roles=("<|User|>", "<|Assistant|>"),
+        messages=(),
+        offset=0,
+        sep_style=SeparatorStyle.DeepSeek,
+        sep="\n\n",
+        sep2="<｜end▁of▁sentence｜>",
+        stop_token_ids=[100001],
+        stop_str=["User:", "<｜end▁of▁sentence｜>"]
+    )
+)
+# register_conv_template(
+#     Conversation(
+#         name="deepseekv2",
+#         system_template="{system_message}",
+#         system_message="",
+#         roles=("User", "Assistant"),
+#         messages=(),
+#         offset=0,
+#         sep_style=SeparatorStyle.DeepSeekV2,
+#         sep="\n<｜sft▁end｜>",
+#         sep2="<｜end▁of▁sentence｜>",
+#         stop_token_ids=[100001],
+#         stop_str=["User:", "<｜end▁of▁sentence｜>"]
+#     )
+# )
+register_conv_template(
+    Conversation(
+        name="deepseekv2",
+        system_template="{system_message}",
+        system_message="",
+        roles=("|<User>|", "|<Assistant>|"),
+        messages=(),
+        offset=0,
+        sep_style=SeparatorStyle.DeepSeekV2,
+        sep="\n<｜sft▁end｜>",
+        sep2="<｜end▁of▁sentence｜>",
+        stop_token_ids=[100001],
+        stop_str=["User:", "<｜end▁of▁sentence｜>"]
+    )
+)
+
+
+register_conv_template(
+    Conversation(
+        name="plain",
+        system_template="",
+        system_message="",
+        roles=("", ""),
+        messages=(),
+        offset=0,
+        sep_style=SeparatorStyle.PLAIN,
+        sep="",
+        sep2="",
+        stop_token_ids=[100001],
+        stop_str=['</s>'],
+    )
+)
+
+
+register_conv_template(
+    Conversation(
+        name="alignment",
+        system_template="",
+        system_message="",
+        roles=("", ""),
+        messages=(),
+        offset=0,
+        sep_style=SeparatorStyle.ALIGNMENT,
+        sep="",
+        sep2="",
+        stop_token_ids=[100001],
+        stop_str=['</s>'],
+    )
+)
+
+
+if __name__ == "__main__":
+    print("deepseek template:")
+    conv = get_conv_template("deepseek")
+    conv.append_message(conv.roles[0], "Hello!")
+    conv.append_message(conv.roles[1], "Hi! This is Tony.")
+    conv.append_message(conv.roles[0], "Who are you?")
+    conv.append_message(conv.roles[1], "I am a helpful assistant.")
+    conv.append_message(conv.roles[0], "How are you?")
+    conv.append_message(conv.roles[1], None)
+    print(conv.get_prompt())
+
+    print("deepseekv2 template:")
+    conv = get_conv_template("deepseekv2")
+    conv.append_message(conv.roles[0], "Hello!")
+    conv.append_message(conv.roles[1], "Hi! This is Tony.")
+    conv.append_message(conv.roles[0], "Who are you?")
+    conv.append_message(conv.roles[1], "I am a helpful assistant.")
+    conv.append_message(conv.roles[0], "How are you?")
+    conv.append_message(conv.roles[1], None)
+    print(conv.get_prompt())