tencent
/

Youtu-LLM-2B-Base

@@ -1,586 +0,0 @@
-# coding=utf-8
-# Copyright 2025 Tencent Youtu lab, DeepSeek-AI and The HuggingFace Inc. team. All rights reserved.
-#
-# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
-# and OPT implementations in this library. It has been modified from its
-# original forms to accommodate minor architectural differences compared
-# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-import math
-from typing import Callable, Optional, Union
-import torch
-import torch.nn.functional as F
-from torch import nn
-from transformers.activations import ACT2FN
-from transformers.cache_utils import Cache, DynamicCache
-from transformers.generation import GenerationMixin
-from transformers.integrations import use_kernel_forward_from_hub
-from transformers.masking_utils import create_causal_mask
-from transformers.modeling_flash_attention_utils import FlashAttentionKwargs
-from transformers.modeling_layers import GradientCheckpointingLayer
-from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast
-from transformers.modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_update
-from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
-from transformers.processing_utils import Unpack
-from transformers.utils import TransformersKwargs, auto_docstring, can_return_tuple
-from transformers.utils.deprecation import deprecate_kwarg
-from transformers.utils.generic import check_model_inputs
-from .configuration_youtu import YoutuConfig
-@use_kernel_forward_from_hub("RMSNorm")
-class YoutuRMSNorm(nn.Module):
-    def __init__(self, hidden_size, eps=1e-6):
-        """
-        YoutuRMSNorm is equivalent to T5LayerNorm
-        """
-        super().__init__()
-        self.weight = nn.Parameter(torch.ones(hidden_size))
-        self.variance_epsilon = eps
-    def forward(self, hidden_states):
-        input_dtype = hidden_states.dtype
-        hidden_states = hidden_states.to(torch.float32)
-        variance = hidden_states.pow(2).mean(-1, keepdim=True)
-        hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
-        return self.weight * hidden_states.to(input_dtype)
-    def extra_repr(self):
-        return f"{tuple(self.weight.shape)}, eps={self.variance_epsilon}"
-class YoutuRotaryEmbedding(nn.Module):
-    inv_freq: torch.Tensor  # fix linting for `register_buffer`
-    def __init__(self, config: YoutuConfig, device=None):
-        super().__init__()
-        # BC: "rope_type" was originally "type"
-        if hasattr(config, "rope_scaling") and config.rope_scaling is not None:
-            self.rope_type = config.rope_scaling.get("rope_type", config.rope_scaling.get("type"))
-        else:
-            self.rope_type = "default"
-        self.max_seq_len_cached = config.max_position_embeddings
-        self.original_max_seq_len = config.max_position_embeddings
-        self.config = config
-        self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
-        inv_freq, self.attention_scaling = self.rope_init_fn(self.config, device)
-        self.register_buffer("inv_freq", inv_freq, persistent=False)
-        self.original_inv_freq = self.inv_freq
-    @torch.no_grad()
-    @dynamic_rope_update  # power user: used with advanced RoPE types (e.g. dynamic rope)
-    def forward(self, x, position_ids):
-        inv_freq_expanded = self.inv_freq[None, :, None].float().expand(position_ids.shape[0], -1, 1).to(x.device)
-        position_ids_expanded = position_ids[:, None, :].float()
-        device_type = x.device.type if isinstance(x.device.type, str) and x.device.type != "mps" else "cpu"
-        with torch.autocast(device_type=device_type, enabled=False):  # Force float32
-            freqs = (inv_freq_expanded.float() @ position_ids_expanded.float()).transpose(1, 2)
-            emb = torch.cat((freqs, freqs), dim=-1)
-            cos = emb.cos() * self.attention_scaling
-            sin = emb.sin() * self.attention_scaling
-        return cos.to(dtype=x.dtype), sin.to(dtype=x.dtype)
-class YoutuMLP(nn.Module):
-    def __init__(self, config, hidden_size=None, intermediate_size=None):
-        super().__init__()
-        self.config = config
-        self.hidden_size = config.hidden_size if hidden_size is None else hidden_size
-        self.intermediate_size = config.intermediate_size if intermediate_size is None else intermediate_size
-        self.mlp_bias = config.mlp_bias
-        self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=self.mlp_bias)
-        self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=self.mlp_bias)
-        self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=self.mlp_bias)
-        self.act_fn = ACT2FN[config.hidden_act]
-    def forward(self, x):
-        down_proj = self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))
-        return down_proj
-def rotate_half(x):
-    """Rotates half the hidden dims of the input."""
-    x1 = x[..., : x.shape[-1] // 2]
-    x2 = x[..., x.shape[-1] // 2 :]
-    return torch.cat((-x2, x1), dim=-1)
-def apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, unsqueeze_dim=1):
-    """Applies Rotary Position Embedding to the query and key tensors.
-    Args:
-        q (`torch.Tensor`): The query tensor.
-        k (`torch.Tensor`): The key tensor.
-        cos (`torch.Tensor`): The cosine part of the rotary embedding.
-        sin (`torch.Tensor`): The sine part of the rotary embedding.
-        position_ids (`torch.Tensor`, *optional*):
-            Deprecated and unused.
-        unsqueeze_dim (`int`, *optional*, defaults to 1):
-            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
-            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
-            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
-            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
-            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
-            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
-    Returns:
-        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
-    """
-    cos = cos.unsqueeze(unsqueeze_dim)
-    sin = sin.unsqueeze(unsqueeze_dim)
-    q_embed = (q * cos) + (rotate_half(q) * sin)
-    k_embed = (k * cos) + (rotate_half(k) * sin)
-    return q_embed, k_embed
-def repeat_kv(hidden_states: torch.Tensor, n_rep: int) -> torch.Tensor:
-    """
-    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
-    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
-    """
-    batch, num_key_value_heads, slen, head_dim = hidden_states.shape
-    if n_rep == 1:
-        return hidden_states
-    hidden_states = hidden_states[:, :, None, :, :].expand(batch, num_key_value_heads, n_rep, slen, head_dim)
-    return hidden_states.reshape(batch, num_key_value_heads * n_rep, slen, head_dim)
-def eager_attention_forward(
-    module: nn.Module,
-    query: torch.Tensor,
-    key: torch.Tensor,
-    value: torch.Tensor,
-    attention_mask: Optional[torch.Tensor],
-    scaling: float,
-    dropout: float = 0.0,
-    **kwargs: Unpack[TransformersKwargs],
-):
-    key_states = repeat_kv(key, module.num_key_value_groups)
-    value_states = repeat_kv(value, module.num_key_value_groups)
-    attn_weights = torch.matmul(query, key_states.transpose(2, 3)) * scaling
-    if attention_mask is not None:
-        causal_mask = attention_mask[:, :, :, : key_states.shape[-2]]
-        attn_weights = attn_weights + causal_mask
-    attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query.dtype)
-    attn_weights = nn.functional.dropout(attn_weights, p=dropout, training=module.training)
-    attn_output = torch.matmul(attn_weights, value_states)
-    attn_output = attn_output.transpose(1, 2).contiguous()
-    return attn_output, attn_weights
-def apply_rotary_pos_emb_interleave(q, k, cos, sin, position_ids=None, unsqueeze_dim=1):
-    r"""
-    TODO let's just use the original freqcis computation to not have the view
-    transpose + reshape! This is not optimized!
-    Applies Rotary Position Embedding to the query and key tensors.
-    Args:
-        q (`torch.Tensor`): The query tensor.
-        k (`torch.Tensor`): The key tensor.
-        cos (`torch.Tensor`): The cosine part of the rotary embedding.
-        sin (`torch.Tensor`): The sine part of the rotary embedding.
-        position_ids (`torch.Tensor`):
-            The position indices of the tokens corresponding to the query and key tensors. For example, this can be
-            used to pass offsetted position ids when working with a KV-cache.
-        unsqueeze_dim (`int`, *optional*, defaults to 1):
-            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
-            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
-            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
-            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
-            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
-            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
-    Returns:
-        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
-    """
-    cos = cos.unsqueeze(unsqueeze_dim)
-    sin = sin.unsqueeze(unsqueeze_dim)
-    b, h, s, d = q.shape
-    q = q.view(b, h, s, d // 2, 2).transpose(4, 3).reshape(b, h, s, d)
-    b, h, s, d = k.shape
-    k = k.view(b, h, s, d // 2, 2).transpose(4, 3).reshape(b, h, s, d)
-    q_embed = (q * cos) + (rotate_half(q) * sin)
-    k_embed = (k * cos) + (rotate_half(k) * sin)
-    return q_embed, k_embed
-def yarn_get_mscale(scale=1, mscale=1):
-    if scale <= 1:
-        return 1.0
-    return 0.1 * mscale * math.log(scale) + 1.0
-class YoutuMLAttention(nn.Module):
-    """Multi-latent attention from 'DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model' paper"""
-    def __init__(self, config: YoutuConfig, layer_idx: int):
-        super().__init__()
-        self.config = config
-        self.layer_idx = layer_idx
-        self.num_key_value_groups = config.num_attention_heads // config.num_key_value_heads
-        self.attention_dropout = config.attention_dropout
-        self.num_heads = config.num_attention_heads
-        self.rope_theta = config.rope_theta
-        self.q_lora_rank = config.q_lora_rank
-        self.qk_rope_head_dim = config.qk_rope_head_dim
-        self.kv_lora_rank = config.kv_lora_rank
-        self.v_head_dim = config.v_head_dim
-        self.qk_nope_head_dim = config.qk_nope_head_dim
-        self.qk_head_dim = config.qk_head_dim
-        self.is_causal = True
-        if self.q_lora_rank is None:
-            self.q_proj = nn.Linear(config.hidden_size, self.num_heads * self.qk_head_dim, bias=False)
-        else:
-            self.q_a_proj = nn.Linear(config.hidden_size, config.q_lora_rank, bias=config.attention_bias)
-            self.q_a_layernorm = YoutuRMSNorm(config.q_lora_rank)
-            self.q_b_proj = nn.Linear(config.q_lora_rank, self.num_heads * self.qk_head_dim, bias=False)
-        self.kv_a_proj_with_mqa = nn.Linear(
-            config.hidden_size,
-            self.kv_lora_rank + self.qk_rope_head_dim,
-            bias=config.attention_bias,
-        )
-        self.kv_a_layernorm = YoutuRMSNorm(self.kv_lora_rank)
-        self.kv_b_proj = nn.Linear(
-            self.kv_lora_rank,
-            self.num_heads * (self.qk_nope_head_dim + self.v_head_dim),
-            bias=False,
-        )
-        self.o_proj = nn.Linear(
-            self.num_heads * self.v_head_dim,
-            config.hidden_size,
-            bias=config.attention_bias,
-        )
-        self.scaling = self.qk_head_dim ** (-0.5)
-        if self.config.rope_scaling is not None:
-            mscale_all_dim = self.config.rope_scaling.get("mscale_all_dim", 0)
-            scaling_factor = self.config.rope_scaling["factor"]
-            if mscale_all_dim:
-                mscale = yarn_get_mscale(scaling_factor, mscale_all_dim)
-                self.scaling = self.scaling * mscale * mscale
-    @deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58")
-    def forward(
-        self,
-        hidden_states: torch.Tensor,
-        position_embeddings: tuple[torch.Tensor, torch.Tensor],
-        attention_mask: Optional[torch.Tensor],
-        past_key_values: Optional[Cache] = None,
-        cache_position: Optional[torch.LongTensor] = None,
-        **kwargs: Unpack[FlashAttentionKwargs],
-    ) -> tuple[torch.Tensor, Optional[torch.Tensor], Optional[tuple[torch.Tensor]]]:
-        batch_size, seq_length = hidden_states.shape[:-1]
-        query_shape = (batch_size, seq_length, -1, self.qk_head_dim)
-        key_shape = (batch_size, seq_length, -1, self.qk_nope_head_dim + self.v_head_dim)
-        if self.q_lora_rank is None:
-            q_states = self.q_proj(hidden_states)
-        else:
-            q_states = self.q_b_proj(self.q_a_layernorm(self.q_a_proj(hidden_states)))
-        q_states = q_states.view(query_shape).transpose(1, 2)
-        q_pass, q_rot = torch.split(q_states, [self.qk_nope_head_dim, self.qk_rope_head_dim], dim=-1)
-        compressed_kv = self.kv_a_proj_with_mqa(hidden_states)
-        k_pass, k_rot = torch.split(compressed_kv, [self.kv_lora_rank, self.qk_rope_head_dim], dim=-1)
-        k_pass = self.kv_b_proj(self.kv_a_layernorm(k_pass)).view(key_shape).transpose(1, 2)
-        k_pass, value_states = torch.split(k_pass, [self.qk_nope_head_dim, self.v_head_dim], dim=-1)
-        k_rot = k_rot.view(batch_size, 1, seq_length, self.qk_rope_head_dim)
-        cos, sin = position_embeddings
-        if self.config.rope_interleave:  # support using interleaved weights for efficiency
-            q_rot, k_rot = apply_rotary_pos_emb_interleave(q_rot, k_rot, cos, sin)
-        else:
-            q_rot, k_rot = apply_rotary_pos_emb(q_rot, k_rot, cos, sin)
-        k_rot = k_rot.expand(*k_pass.shape[:-1], -1)
-        query_states = torch.cat((q_pass, q_rot), dim=-1)
-        key_states = torch.cat((k_pass, k_rot), dim=-1)
-        if past_key_values is not None:
-            # sin and cos are specific to RoPE models; cache_position needed for the static cache
-            cache_kwargs = {"sin": sin, "cos": cos, "cache_position": cache_position}
-            key_states, value_states = past_key_values.update(key_states, value_states, self.layer_idx, cache_kwargs)
-        if self.config._attn_implementation == "flash_attention_2" and self.qk_head_dim != self.v_head_dim:
-            value_states = F.pad(value_states, [0, self.qk_head_dim - self.v_head_dim])
-        attention_interface: Callable = eager_attention_forward
-        if self.config._attn_implementation != "eager":
-            attention_interface = ALL_ATTENTION_FUNCTIONS[self.config._attn_implementation]
-        attn_output, attn_weights = attention_interface(
-            self,
-            query_states,
-            key_states,
-            value_states,
-            attention_mask,
-            dropout=0.0 if not self.training else self.attention_dropout,
-            scaling=self.scaling,
-            **kwargs,
-        )
-        if self.config._attn_implementation == "flash_attention_2" and self.qk_head_dim != self.v_head_dim:
-            attn_output = attn_output[:, :, :, : self.v_head_dim]
-        attn_output = attn_output.reshape(batch_size, seq_length, -1).contiguous()
-        attn_output = self.o_proj(attn_output)
-        return attn_output, attn_weights
-class YoutuDecoderLayer(GradientCheckpointingLayer):
-    def __init__(self, config: YoutuConfig, layer_idx: int):
-        super().__init__()
-        self.hidden_size = config.hidden_size
-        self.self_attn = YoutuMLAttention(config=config, layer_idx=layer_idx)
-        self.mlp = YoutuMLP(config)
-        self.input_layernorm = YoutuRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
-        self.post_attention_layernorm = YoutuRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
-    @deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58")
-    def forward(
-        self,
-        hidden_states: torch.Tensor,
-        attention_mask: Optional[torch.Tensor] = None,
-        position_ids: Optional[torch.LongTensor] = None,
-        past_key_values: Optional[Cache] = None,
-        use_cache: Optional[bool] = False,
-        cache_position: Optional[torch.LongTensor] = None,
-        position_embeddings: Optional[tuple[torch.Tensor, torch.Tensor]] = None,  # necessary, but kept here for BC
-        **kwargs: Unpack[TransformersKwargs],
-    ) -> torch.Tensor:
-        residual = hidden_states
-        hidden_states = self.input_layernorm(hidden_states)
-        # Self Attention
-        hidden_states, _ = self.self_attn(
-            hidden_states=hidden_states,
-            attention_mask=attention_mask,
-            position_ids=position_ids,
-            past_key_values=past_key_values,
-            use_cache=use_cache,
-            cache_position=cache_position,
-            position_embeddings=position_embeddings,
-            **kwargs,
-        )
-        hidden_states = residual + hidden_states
-        # Fully Connected
-        residual = hidden_states
-        hidden_states = self.post_attention_layernorm(hidden_states)
-        hidden_states = self.mlp(hidden_states)
-        hidden_states = residual + hidden_states
-        return hidden_states
-@auto_docstring
-class YoutuPreTrainedModel(PreTrainedModel):
-    config: YoutuConfig
-    base_model_prefix = "model"
-    supports_gradient_checkpointing = True
-    _no_split_modules = ["YoutuDecoderLayer"]
-    _skip_keys_device_placement = ["past_key_values"]
-    _supports_flash_attn = True
-    _supports_sdpa = True
-    _supports_flex_attn = True
-    _can_compile_fullgraph = False
-    _supports_attention_backend = True
-    _can_record_outputs = {
-        "hidden_states": YoutuDecoderLayer,
-        "attentions": YoutuMLAttention,
-    }
-    def _init_weights(self, module):
-        super()._init_weights(module)
-        std = self.config.initializer_range
-        embedding_std = self.config.embedding_initializer_range
-        if isinstance(module, nn.Linear):
-            module.weight.data.normal_(mean=0.0, std=std)
-            if module.bias is not None:
-                module.bias.data.zero_()
-        elif isinstance(module, nn.Embedding):
-            module.weight.data.normal_(mean=0.0, std=embedding_std)
-            if module.padding_idx is not None:
-                module.weight.data[module.padding_idx].zero_()
-@auto_docstring
-class YoutuModel(YoutuPreTrainedModel):
-    _keys_to_ignore_on_load_unexpected = [""]
-    def __init__(self, config: YoutuConfig):
-        super().__init__(config)
-        self.padding_idx = config.pad_token_id
-        self.vocab_size = config.vocab_size
-        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
-        self.layers = nn.ModuleList(
-            [YoutuDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
-        )
-        self.norm = YoutuRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
-        self.rotary_emb = YoutuRotaryEmbedding(config=config)
-        self.gradient_checkpointing = False
-        # Initialize weights and apply final processing
-        self.post_init()
-    @check_model_inputs
-    @auto_docstring
-    def forward(
-        self,
-        input_ids: Optional[torch.LongTensor] = None,
-        attention_mask: Optional[torch.Tensor] = None,
-        position_ids: Optional[torch.LongTensor] = None,
-        past_key_values: Optional[Cache] = None,
-        inputs_embeds: Optional[torch.FloatTensor] = None,
-        cache_position: Optional[torch.LongTensor] = None,
-        use_cache: Optional[bool] = None,
-        **kwargs: Unpack[TransformersKwargs],
-    ) -> BaseModelOutputWithPast:
-        if (input_ids is None) ^ (inputs_embeds is not None):
-            raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
-        if inputs_embeds is None:
-            inputs_embeds: torch.Tensor = self.embed_tokens(input_ids)
-        if use_cache and past_key_values is None:
-            past_key_values = DynamicCache(config=self.config)
-        if cache_position is None:
-            past_seen_tokens = past_key_values.get_seq_length() if past_key_values is not None else 0
-            cache_position: torch.Tensor = torch.arange(
-                past_seen_tokens, past_seen_tokens + inputs_embeds.shape[1], device=inputs_embeds.device
-            )
-        if position_ids is None:
-            position_ids = cache_position.unsqueeze(0)
-        causal_mask = create_causal_mask(
-            config=self.config,
-            input_embeds=inputs_embeds,
-            attention_mask=attention_mask,
-            cache_position=cache_position,
-            past_key_values=past_key_values,
-            position_ids=position_ids,
-        )
-        hidden_states = inputs_embeds
-        position_embeddings = self.rotary_emb(hidden_states, position_ids)
-        for decoder_layer in self.layers[: self.config.num_hidden_layers]:
-            hidden_states = decoder_layer(
-                hidden_states,
-                attention_mask=causal_mask,
-                position_ids=position_ids,
-                past_key_values=past_key_values,
-                cache_position=cache_position,
-                position_embeddings=position_embeddings,
-                **kwargs,
-            )
-        hidden_states = self.norm(hidden_states)
-        return BaseModelOutputWithPast(
-            last_hidden_state=hidden_states,
-            past_key_values=past_key_values,
-        )
-@auto_docstring
-class YoutuForCausalLM(YoutuPreTrainedModel, GenerationMixin):
-    _tied_weights_keys = ["lm_head.weight"]
-    _tp_plan = {"lm_head": "colwise_rep"}
-    _pp_plan = {"lm_head": (["hidden_states"], ["logits"])}
-    def __init__(self, config):
-        super().__init__(config)
-        self.model = YoutuModel(config)
-        self.vocab_size = config.vocab_size
-        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
-        # Initialize weights and apply final processing
-        self.post_init()
-    @can_return_tuple
-    @auto_docstring
-    def forward(
-        self,
-        input_ids: Optional[torch.LongTensor] = None,
-        attention_mask: Optional[torch.Tensor] = None,
-        position_ids: Optional[torch.LongTensor] = None,
-        past_key_values: Optional[Cache] = None,
-        inputs_embeds: Optional[torch.FloatTensor] = None,
-        labels: Optional[torch.LongTensor] = None,
-        use_cache: Optional[bool] = None,
-        cache_position: Optional[torch.LongTensor] = None,
-        logits_to_keep: Union[int, torch.Tensor] = 0,
-        **kwargs: Unpack[TransformersKwargs],
-    ) -> CausalLMOutputWithPast:
-        r"""
-        Example:
-        ```python
-        >>> from transformers import YoutuTokenizer, YoutuForCausalLM
-        >>> model = YoutuForCausalLM.from_pretrained("tencent/Youtu-LLM-2B")
-        >>> tokenizer = YoutuTokenizer.from_pretrained("tencent/Youtu-LLM-2B")
-        >>> prompt = "Hey, are you conscious? Can you talk to me?"
-        >>> inputs = tokenizer(prompt, return_tensors="pt")
-        >>> # Generate
-        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
-        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
-        ```"""
-        outputs: BaseModelOutputWithPast = self.model(
-            input_ids=input_ids,
-            attention_mask=attention_mask,
-            position_ids=position_ids,
-            past_key_values=past_key_values,
-            inputs_embeds=inputs_embeds,
-            use_cache=use_cache,
-            cache_position=cache_position,
-            **kwargs,
-        )
-        hidden_states = outputs.last_hidden_state
-        # Only compute necessary logits, and do not upcast them to float if we are not computing the loss
-        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
-        logits = self.lm_head(hidden_states[:, slice_indices, :])
-        loss = None
-        if labels is not None:
-            loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size, **kwargs)
-        return CausalLMOutputWithPast(
-            loss=loss,
-            logits=logits,
-            past_key_values=outputs.past_key_values,
-            hidden_states=outputs.hidden_states,
-            attentions=outputs.attentions,
-        )
-__all__ = ["YoutuPreTrainedModel", "YoutuModel", "YoutuForCausalLM"]