update

README.md

@@ -13,23 +13,32 @@ inference: false
 pipeline_tag: text-generation
 ---
 
-# glm-4-9b
+# glm-4-9b-hf
 
-Read this in [English](README.md).
+请阅读 [中文版本](README_zh.md).
 
-如果您使用的是这个仓库中的权重，请更新到
+If you are using the weights from this repository, please update to 
 
 <span style="color:red; font-weight:bold;"> transformers>=4.46.0 </span>
 
-这些权重 **不兼容** 较早版本的 transformers 库。
+These weights are **not compatible** with older versions of the transformers library.
 
-GLM-4-9B 是智谱 AI 推出的最新一代预训练模型 GLM-4 系列中的开源版本。
-在语义、数学、推理、代码和知识等多方面的数据集测评中，GLM-4-9B 及其人类偏好对齐的版本 GLM-4-9B-Chat 均表现出较高的性能。
-除了能进行多轮对话，GLM-4-9B-Chat 还具备网页浏览、代码执行、自定义工具调用（Function Call）和长文本推理（支持最大 128K
-上下文）等高级功能。
-本代模型增加了多语言支持，支持包括日语，韩语，德语在内的 26 种语言。我们还推出了支持 1M 上下文长度（约 200 万中文字符）的模型。
+## Model Introduction
 
-我们在一些典型任务上对 GLM-4-9B 基座模型进行了评测，结果如下：
+GLM-4-9B is the open-source version of the latest generation of pre-trained models in the GLM-4 series launched by Zhipu
+AI. In the evaluation of data sets in semantics, mathematics, reasoning, code, and knowledge, **GLM-4-9B**
+and its human preference-aligned version **GLM-4-9B-Chat** have shown superior performance beyond Llama-3-8B. In
+addition to multi-round conversations, GLM-4-9B-Chat also has advanced features such as web browsing, code execution,
+custom tool calls (Function Call), and long text
+reasoning (supporting up to 128K context). This generation of models has added multi-language support, supporting 26
+languages including Japanese, Korean, and German. We have also launched the **GLM-4-9B-Chat-1M** model that supports 1M
+context length (about 2 million Chinese characters) and the multimodal model GLM-4V-9B based on GLM-4-9B.
+**GLM-4V-9B** possesses dialogue capabilities in both Chinese and English at a high resolution of 1120*1120.
+In various multimodal evaluations, including comprehensive abilities in Chinese and English, perception & reasoning,
+text recognition, and chart understanding, GLM-4V-9B demonstrates superior performance compared to
+GPT-4-turbo-2024-04-09, Gemini 1.0 Pro, Qwen-VL-Max, and Claude 3 Opus.
+
+We evaluated the GLM-4-9B base model on some typical tasks, and the results are as follows:
 
 | Model               |   MMLU   |  C-Eval  |   GPQA   |  GSM8K   |   MATH   | HumanEval |
 |:--------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:---------:|
@@ -38,17 +47,18 @@ GLM-4-9B 是智谱 AI 推出的最新一代预训练模型 GLM-4 系列中的开
 | ChatGLM3-6B-Base    |   61.4   |   69.0   |    -     |   72.3   |   25.7   |     -     |
 | GLM-4-9B            | **74.7** | **77.1** | **34.3** | **84.0** | **30.4** | **70.1**  |
 
-更多推理代码和依赖信息，请访问我们的 [github](https://github.com/THUDM/GLM-4) 。
+**This repository is the base version of GLM-4-9B, supporting 8K context length.**
+
+For more inference code and requirements, please visit our [github page](https://github.com/THUDM/GLM-4).
 
-**本仓库是 GLM-4-9B 的基座版本，支持`8K`上下文长度。**
+## LICENSE
 
-## 协议
+The weights of the GLM-4 model are available under the terms of [LICENSE](LICENSE).
 
-GLM-4 模型的权重的使用则需要遵循 [LICENSE](LICENSE)。
 
-## 引用
+## Citations
 
-如果你觉得我们的工作有帮助的话，请考虑引用下列论文。
+If you find our work useful, please consider citing the following paper.
 
 ```
 @misc{glm2024chatglm,
@@ -59,4 +69,4 @@ GLM-4 模型的权重的使用则需要遵循 [LICENSE](LICENSE)。
       archivePrefix={arXiv},
       primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
 }
-```
+```

configuration_chatglm.py

@@ -1,58 +0,0 @@
-from transformers import PretrainedConfig
-
-
-class ChatGLMConfig(PretrainedConfig):
-    model_type = "chatglm"
-
-    def __init__(
-            self,
-            num_layers=28,
-            padded_vocab_size=65024,
-            hidden_size=4096,
-            ffn_hidden_size=13696,
-            kv_channels=128,
-            num_attention_heads=32,
-            seq_length=2048,
-            hidden_dropout=0.0,
-            classifier_dropout=None,
-            attention_dropout=0.0,
-            layernorm_epsilon=1e-5,
-            rmsnorm=True,
-            apply_residual_connection_post_layernorm=False,
-            post_layer_norm=True,
-            add_bias_linear=False,
-            add_qkv_bias=False,
-            bias_dropout_fusion=True,
-            multi_query_attention=False,
-            multi_query_group_num=1,
-            rope_ratio=1,
-            apply_query_key_layer_scaling=True,
-            attention_softmax_in_fp32=True,
-            fp32_residual_connection=False,
-            **kwargs
-    ):
-        self.num_layers = num_layers
-        self.vocab_size = padded_vocab_size
-        self.padded_vocab_size = padded_vocab_size
-        self.hidden_size = hidden_size
-        self.ffn_hidden_size = ffn_hidden_size
-        self.kv_channels = kv_channels
-        self.num_attention_heads = num_attention_heads
-        self.seq_length = seq_length
-        self.hidden_dropout = hidden_dropout
-        self.classifier_dropout = classifier_dropout
-        self.attention_dropout = attention_dropout
-        self.layernorm_epsilon = layernorm_epsilon
-        self.rmsnorm = rmsnorm
-        self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
-        self.post_layer_norm = post_layer_norm
-        self.add_bias_linear = add_bias_linear
-        self.add_qkv_bias = add_qkv_bias
-        self.bias_dropout_fusion = bias_dropout_fusion
-        self.multi_query_attention = multi_query_attention
-        self.multi_query_group_num = multi_query_group_num
-        self.rope_ratio = rope_ratio
-        self.apply_query_key_layer_scaling = apply_query_key_layer_scaling
-        self.attention_softmax_in_fp32 = attention_softmax_in_fp32
-        self.fp32_residual_connection = fp32_residual_connection
-        super().__init__(**kwargs)

modeling_chatglm.py

@@ -1,1141 +0,0 @@
-""" PyTorch ChatGLM model. """
-import json
-import math
-import copy
-import warnings
-import re
-import sys
-
-import torch
-import torch.utils.checkpoint
-import torch.nn.functional as F
-from torch import nn
-from torch.nn import CrossEntropyLoss, LayerNorm, MSELoss, BCEWithLogitsLoss
-from torch.nn.utils import skip_init
-from typing import Optional, Tuple, Union, List, Callable, Dict, Any
-from copy import deepcopy
-
-from transformers.modeling_outputs import (
-    BaseModelOutputWithPast,
-    CausalLMOutputWithPast,
-    SequenceClassifierOutputWithPast,
-)
-from transformers.modeling_utils import PreTrainedModel
-from transformers.utils import logging, is_torch_npu_available
-from transformers.generation.logits_process import LogitsProcessor
-from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig, ModelOutput
-
-from .configuration_chatglm import ChatGLMConfig
-
-try:
-    from transformers.utils import is_flash_attn_greater_or_equal_2_10, is_flash_attn_2_available
-    if is_flash_attn_2_available():
-        from flash_attn import flash_attn_func, flash_attn_varlen_func
-        from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input  # noqa
-except:
-    pass
-
-
-# flags required to enable jit fusion kernels
-
-if sys.platform != 'darwin' and not is_torch_npu_available():
-    torch._C._jit_set_profiling_mode(False)
-    torch._C._jit_set_profiling_executor(False)
-    torch._C._jit_override_can_fuse_on_cpu(True)
-    torch._C._jit_override_can_fuse_on_gpu(True)
-
-logger = logging.get_logger(__name__)
-
-_CHECKPOINT_FOR_DOC = "THUDM/ChatGLM"
-_CONFIG_FOR_DOC = "ChatGLMConfig"
-
-
-def default_init(cls, *args, **kwargs):
-    return cls(*args, **kwargs)
-
-
-class InvalidScoreLogitsProcessor(LogitsProcessor):
-    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor:
-        if torch.isnan(scores).any() or torch.isinf(scores).any():
-            scores.zero_()
-            scores[..., 198] = 5e4
-        return scores
-
-
-def split_tensor_along_last_dim(
-        tensor: torch.Tensor,
-        num_partitions: int,
-        contiguous_split_chunks: bool = False,
-) -> List[torch.Tensor]:
-    """Split a tensor along its last dimension.
-
-    Arguments:
-        tensor: input tensor.
-        num_partitions: number of partitions to split the tensor
-        contiguous_split_chunks: If True, make each chunk contiguous
-                                 in memory.
-
-    Returns:
-        A list of Tensors
-    """
-    # Get the size and dimension.
-    last_dim = tensor.dim() - 1
-    last_dim_size = tensor.size()[last_dim] // num_partitions
-    # Split.
-    tensor_list = torch.split(tensor, last_dim_size, dim=last_dim)
-    # Note: torch.split does not create contiguous tensors by default.
-    if contiguous_split_chunks:
-        return tuple(chunk.contiguous() for chunk in tensor_list)
-
-    return tensor_list
-
-
-class RotaryEmbedding(nn.Module):
-    def __init__(self, dim, rope_ratio=1, original_impl=False, device=None, dtype=None):
-        super().__init__()
-        inv_freq = 1.0 / (10000 ** (torch.arange(0, dim, 2, device=device).to(dtype=dtype) / dim))
-        self.register_buffer("inv_freq", inv_freq)
-        self.dim = dim
-        self.original_impl = original_impl
-        self.rope_ratio = rope_ratio
-
-    def forward_impl(
-            self, seq_len: int, n_elem: int, dtype: torch.dtype, device: torch.device, base: int = 10000
-    ):
-        """Enhanced Transformer with Rotary Position Embedding.
-
-        Derived from: https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/
-        transformers/rope/__init__.py. MIT License:
-        https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/license.
-        """
-        # $\Theta = {\theta_i = 10000^{\frac{2(i-1)}{d}}, i \in [1, 2, ..., \frac{d}{2}]}$
-        base = base * self.rope_ratio
-        theta = 1.0 / (base ** (torch.arange(0, n_elem, 2, dtype=torch.float, device=device) / n_elem))
-
-        # Create position indexes `[0, 1, ..., seq_len - 1]`
-        seq_idx = torch.arange(seq_len, dtype=torch.float, device=device)
-
-        # Calculate the product of position index and $\theta_i$
-        idx_theta = torch.outer(seq_idx, theta).float()
-
-        cache = torch.stack([torch.cos(idx_theta), torch.sin(idx_theta)], dim=-1)
-
-        # this is to mimic the behaviour of complex32, else we will get different results
-        if dtype in (torch.float16, torch.bfloat16, torch.int8):
-            cache = cache.bfloat16() if dtype == torch.bfloat16 else cache.half()
-        return cache
-
-    def forward(self, max_seq_len, offset=0):
-        return self.forward_impl(
-            max_seq_len, self.dim, dtype=self.inv_freq.dtype, device=self.inv_freq.device
-        )
-
-
-@torch.jit.script
-def apply_rotary_pos_emb(x: torch.Tensor, rope_cache: torch.Tensor) -> torch.Tensor:
-    # x: [b, np, sq, hn]
-    b, np, sq, hn = x.size(0), x.size(1), x.size(2), x.size(3)
-    rot_dim = rope_cache.shape[-2] * 2
-    x, x_pass = x[..., :rot_dim], x[..., rot_dim:]
-    # truncate to support variable sizes
-    rope_cache = rope_cache[:, :sq]
-    xshaped = x.reshape(b, np, sq, rot_dim // 2, 2)
-    rope_cache = rope_cache.view(-1, 1, sq, xshaped.size(3), 2)
-    x_out2 = torch.stack(
-        [
-            xshaped[..., 0] * rope_cache[..., 0] - xshaped[..., 1] * rope_cache[..., 1],
-            xshaped[..., 1] * rope_cache[..., 0] + xshaped[..., 0] * rope_cache[..., 1],
-        ],
-        -1,
-    )
-    x_out2 = x_out2.flatten(3)
-    return torch.cat((x_out2, x_pass), dim=-1)
-
-
-class RMSNorm(torch.nn.Module):
-    def __init__(self, normalized_shape, eps=1e-5, device=None, dtype=None, **kwargs):
-        super().__init__()
-        self.weight = torch.nn.Parameter(torch.empty(normalized_shape, device=device, dtype=dtype))
-        self.eps = eps
-
-    def forward(self, hidden_states: torch.Tensor):
-        input_dtype = hidden_states.dtype
-        variance = hidden_states.to(torch.float32).pow(2).mean(-1, keepdim=True)
-        hidden_states = hidden_states * torch.rsqrt(variance + self.eps)
-
-        return (self.weight * hidden_states).to(input_dtype)
-
-
-class CoreAttention(torch.nn.Module):
-    def __init__(self, config: ChatGLMConfig, layer_number):
-        super(CoreAttention, self).__init__()
-        self.config = config
-        self.apply_query_key_layer_scaling = config.apply_query_key_layer_scaling
-        self.attention_softmax_in_fp32 = config.attention_softmax_in_fp32
-        if self.apply_query_key_layer_scaling:
-            self.attention_softmax_in_fp32 = True
-        self.layer_number = max(1, layer_number)
-        self.is_causal = True
-
-        projection_size = config.kv_channels * config.num_attention_heads
-
-        # Per attention head and per partition values.
-        self.hidden_size_per_partition = projection_size
-        self.hidden_size_per_attention_head = projection_size // config.num_attention_heads
-        self.num_attention_heads_per_partition = config.num_attention_heads
-
-        coeff = None
-        self.norm_factor = math.sqrt(self.hidden_size_per_attention_head)
-        if self.apply_query_key_layer_scaling:
-            coeff = self.layer_number
-            self.norm_factor *= coeff
-        self.coeff = coeff
-
-        self.attention_dropout = torch.nn.Dropout(config.attention_dropout)
-
-    def forward(self, query_layer, key_layer, value_layer, attention_mask):
-        # [b, np, sq, sk]
-        output_size = (query_layer.size(0), query_layer.size(1), query_layer.size(2), key_layer.size(2))
-
-        # [b, np, sq, hn] -> [b * np, sq, hn]
-        query_layer = query_layer.view(output_size[0] * output_size[1], output_size[2], -1)
-        # [b, np, sk, hn] -> [b * np, sk, hn]
-        key_layer = key_layer.view(output_size[0] * output_size[1], output_size[3], -1)
-
-        # preallocting input tensor: [b * np, sq, sk]
-        matmul_input_buffer = torch.empty(
-            output_size[0] * output_size[1], output_size[2], output_size[3], dtype=query_layer.dtype,
-            device=query_layer.device
-        )
-
-        # Raw attention scores. [b * np, sq, sk]
-        matmul_result = torch.baddbmm(
-            matmul_input_buffer,
-            query_layer,  # [b * np, sq, hn]
-            key_layer.transpose(1, 2),  # [b * np, hn, sk]
-            beta=0.0,
-            alpha=(1.0 / self.norm_factor),
-        )
-
-        # change view to [b, np, sq, sk]
-        attention_scores = matmul_result.view(*output_size)
-
-        # ===========================
-        # Attention probs and dropout
-        # ===========================
-
-        # attention scores and attention mask [b, np, sq, sk]
-        if self.attention_softmax_in_fp32:
-            attention_scores = attention_scores.float()
-        if self.coeff is not None:
-            attention_scores = attention_scores * self.coeff
-        if attention_mask is None and attention_scores.shape[2] == attention_scores.shape[3]:
-            attention_mask = torch.ones(output_size[0], 1, output_size[2], output_size[3],
-                                        device=attention_scores.device, dtype=torch.bool)
-            attention_mask.tril_()
-            attention_mask = ~attention_mask
-        if attention_mask is not None:
-            attention_scores = attention_scores.masked_fill(attention_mask, float("-inf"))
-        attention_probs = F.softmax(attention_scores, dim=-1)
-        attention_probs = attention_probs.type_as(value_layer)
-
-        # This is actually dropping out entire tokens to attend to, which might
-        # seem a bit unusual, but is taken from the original Transformer paper.
-        attention_probs = self.attention_dropout(attention_probs)
-
-        # query layer shape: [b * np, sq, hn]
-        # value layer shape: [b, np, sk, hn]
-        # attention shape: [b, np, sq, sk]
-        # context layer shape: [b, np, sq, hn]
-        output_size = (value_layer.size(0), value_layer.size(1), query_layer.size(1), value_layer.size(3))
-        # change view [b * np, sk, hn]
-        value_layer = value_layer.view(output_size[0] * output_size[1], value_layer.size(2), -1)
-        # change view [b * np, sq, sk]
-        attention_probs = attention_probs.view(output_size[0] * output_size[1], output_size[2], -1)
-        # matmul: [b * np, sq, hn]
-        context_layer = torch.bmm(attention_probs, value_layer)
-        # change view [b, np, sq, hn]
-        context_layer = context_layer.view(*output_size)
-        # [b, np, sq, hn] --> [b, sq, np, hn]
-        context_layer = context_layer.transpose(1, 2).contiguous()
-        # [b, sq, np, hn] --> [b, sq, hp]
-        new_context_layer_shape = context_layer.size()[:-2] + (self.hidden_size_per_partition,)
-        context_layer = context_layer.reshape(*new_context_layer_shape)
-
-        return context_layer
-
-
-class SdpaAttention(CoreAttention):
-    def forward(self, query_layer, key_layer, value_layer, attention_mask):
-        if attention_mask is None and query_layer.shape[2] == key_layer.shape[2]:
-            context_layer = torch.nn.functional.scaled_dot_product_attention(query_layer, key_layer, value_layer,
-                                                                             is_causal=True,
-                                                                             dropout_p=self.config.attention_dropout if self.training else 0.0)
-        else:
-            if attention_mask is not None:
-                attention_mask = ~attention_mask
-            context_layer = torch.nn.functional.scaled_dot_product_attention(query_layer, key_layer, value_layer,
-                                                                             attention_mask,
-                                                                             dropout_p=self.config.attention_dropout if self.training else 0.0)
-        context_layer = context_layer.transpose(1, 2).contiguous()
-        new_context_layer_shape = context_layer.size()[:-2] + (self.hidden_size_per_partition,)
-        context_layer = context_layer.reshape(*new_context_layer_shape)
-        return context_layer
-
-
-def _get_unpad_data(attention_mask):
-    seqlens_in_batch = attention_mask.sum(dim=-1, dtype=torch.int32)
-    indices = torch.nonzero(attention_mask.flatten(), as_tuple=False).flatten()
-    max_seqlen_in_batch = seqlens_in_batch.max().item()
-    cu_seqlens = F.pad(torch.cumsum(seqlens_in_batch, dim=0, dtype=torch.int32), (1, 0))
-    return (
-        indices,
-        cu_seqlens,
-        max_seqlen_in_batch,
-    )
-
-
-# Copied from transformers.models.llama.modeling_llama.LlamaFlashAttention2
-class FlashAttention2(CoreAttention):
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self._flash_attn_uses_top_left_mask = not is_flash_attn_greater_or_equal_2_10()
-
-    def forward(self, query_states, key_states, value_states, attention_mask):
-        query_states = query_states.transpose(1, 2)
-        key_states = key_states.transpose(1, 2)
-        value_states = value_states.transpose(1, 2)
-        batch_size, query_length = query_states.shape[:2]
-        if not self._flash_attn_uses_top_left_mask:
-            causal = self.is_causal
-        else:
-            # TODO: Remove the `query_length != 1` check once Flash Attention for RoCm is bumped to 2.1. For details, please see the comment in LlamaFlashAttention2 __init__.
-            causal = self.is_causal and query_length != 1
-        dropout = self.config.attention_dropout if self.training else 0.0
-        # Contains at least one padding token in the sequence
-        if attention_mask is not None:
-            query_states, key_states, value_states, indices_q, cu_seq_lens, max_seq_lens = self._upad_input(
-                query_states, key_states, value_states, attention_mask, query_length
-            )
-
-            cu_seqlens_q, cu_seqlens_k = cu_seq_lens
-            max_seqlen_in_batch_q, max_seqlen_in_batch_k = max_seq_lens
-
-            attn_output_unpad = flash_attn_varlen_func(
-                query_states,
-                key_states,
-                value_states,
-                cu_seqlens_q=cu_seqlens_q,
-                cu_seqlens_k=cu_seqlens_k,
-                max_seqlen_q=max_seqlen_in_batch_q,
-                max_seqlen_k=max_seqlen_in_batch_k,
-                dropout_p=dropout,
-                softmax_scale=None,
-                causal=causal,
-            )
-
-            attn_output = pad_input(attn_output_unpad, indices_q, batch_size, query_length)
-        else:
-            attn_output = flash_attn_func(
-                query_states, key_states, value_states, dropout, softmax_scale=None, causal=causal
-            )
-        attn_output = attn_output.reshape(batch_size, query_length, self.hidden_size_per_partition).contiguous()
-        return attn_output
-
-    def _upad_input(self, query_layer, key_layer, value_layer, attention_mask, query_length):
-        indices_k, cu_seqlens_k, max_seqlen_in_batch_k = _get_unpad_data(attention_mask)
-        batch_size, kv_seq_len, num_key_value_heads, head_dim = key_layer.shape
-
-        key_layer = index_first_axis(
-            key_layer.reshape(batch_size * kv_seq_len, num_key_value_heads, head_dim), indices_k
-        )
-        value_layer = index_first_axis(
-            value_layer.reshape(batch_size * kv_seq_len, num_key_value_heads, head_dim), indices_k
-        )
-        if query_length == kv_seq_len:
-            query_layer = index_first_axis(
-                query_layer.reshape(batch_size * kv_seq_len, self.num_attention_heads_per_partition, head_dim), indices_k
-            )
-            cu_seqlens_q = cu_seqlens_k
-            max_seqlen_in_batch_q = max_seqlen_in_batch_k
-            indices_q = indices_k
-        elif query_length == 1:
-            max_seqlen_in_batch_q = 1
-            cu_seqlens_q = torch.arange(
-                batch_size + 1, dtype=torch.int32, device=query_layer.device
-            )  # There is a memcpy here, that is very bad.
-            indices_q = cu_seqlens_q[:-1]
-            query_layer = query_layer.squeeze(1)
-        else:
-            # The -q_len: slice assumes left padding.
-            attention_mask = attention_mask[:, -query_length:]
-            query_layer, indices_q, cu_seqlens_q, max_seqlen_in_batch_q = unpad_input(query_layer, attention_mask)
-
-        return (
-            query_layer,
-            key_layer,
-            value_layer,
-            indices_q,
-            (cu_seqlens_q, cu_seqlens_k),
-            (max_seqlen_in_batch_q, max_seqlen_in_batch_k),
-        )
-
-
-CORE_ATTENTION_CLASSES = {
-    "eager": CoreAttention,
-    "sdpa": SdpaAttention,
-    "flash_attention_2": FlashAttention2
-}
-
-
-class SelfAttention(torch.nn.Module):
-    """Parallel self-attention layer abstract class.
-
-    Self-attention layer takes input with size [s, b, h]
-    and returns output of the same size.
-    """
-
-    def __init__(self, config: ChatGLMConfig, layer_number, device=None):
-        super(SelfAttention, self).__init__()
-        self.layer_number = max(1, layer_number)
-
-        self.projection_size = config.kv_channels * config.num_attention_heads
-
-        # Per attention head and per partition values.
-        self.hidden_size_per_attention_head = self.projection_size // config.num_attention_heads
-        self.num_attention_heads_per_partition = config.num_attention_heads
-
-        self.multi_query_attention = config.multi_query_attention
-        self.qkv_hidden_size = 3 * self.projection_size
-        if self.multi_query_attention:
-            self.num_multi_query_groups_per_partition = config.multi_query_group_num
-            self.qkv_hidden_size = (
-                    self.projection_size + 2 * self.hidden_size_per_attention_head * config.multi_query_group_num
-            )
-        self.query_key_value = nn.Linear(config.hidden_size, self.qkv_hidden_size,
-                                         bias=config.add_bias_linear or config.add_qkv_bias,
-                                         device=device, **_config_to_kwargs(config)
-                                         )
-
-        self.core_attention = CORE_ATTENTION_CLASSES[config._attn_implementation](config, self.layer_number)
-
-        # Output.
-        self.dense = nn.Linear(self.projection_size, config.hidden_size, bias=config.add_bias_linear,
-                               device=device, **_config_to_kwargs(config)
-                               )
-
-    def _allocate_memory(self, inference_max_sequence_len, batch_size, device=None, dtype=None):
-        if self.multi_query_attention:
-            num_attention_heads = self.num_multi_query_groups_per_partition
-        else:
-            num_attention_heads = self.num_attention_heads_per_partition
-        return torch.empty(
-            inference_max_sequence_len,
-            batch_size,
-            num_attention_heads,
-            self.hidden_size_per_attention_head,
-            dtype=dtype,
-            device=device,
-        )
-
-    def forward(
-            self, hidden_states, attention_mask, rotary_pos_emb, kv_cache=None, use_cache=True
-    ):
-        # hidden_states: [b, sq, h]
-
-        # =================================================
-        # Pre-allocate memory for key-values for inference.
-        # =================================================
-        # =====================
-        # Query, Key, and Value
-        # =====================
-
-        # Attention heads [b, sq, h] --> [b, sq, (np * 3 * hn)]
-        mixed_x_layer = self.query_key_value(hidden_states)
-
-        if self.multi_query_attention:
-            (query_layer, key_layer, value_layer) = mixed_x_layer.split(
-                [
-                    self.num_attention_heads_per_partition * self.hidden_size_per_attention_head,
-                    self.num_multi_query_groups_per_partition * self.hidden_size_per_attention_head,
-                    self.num_multi_query_groups_per_partition * self.hidden_size_per_attention_head,
-                ],
-                dim=-1,
-            )
-            query_layer = query_layer.view(
-                query_layer.size()[:-1] + (self.num_attention_heads_per_partition, self.hidden_size_per_attention_head)
-            )
-            key_layer = key_layer.view(
-                key_layer.size()[:-1] + (self.num_multi_query_groups_per_partition, self.hidden_size_per_attention_head)
-            )
-            value_layer = value_layer.view(
-                value_layer.size()[:-1]
-                + (self.num_multi_query_groups_per_partition, self.hidden_size_per_attention_head)
-            )
-        else:
-            new_tensor_shape = mixed_x_layer.size()[:-1] + \
-                               (self.num_attention_heads_per_partition,
-                                3 * self.hidden_size_per_attention_head)
-            mixed_x_layer = mixed_x_layer.view(*new_tensor_shape)
-
-            # [b, sq, np, 3 * hn] --> 3 [b, sq, np, hn]
-            (query_layer, key_layer, value_layer) = split_tensor_along_last_dim(mixed_x_layer, 3)
-
-        # [b, sq, np, hn] -> [b, np, sq, hn]
-        query_layer, key_layer, value_layer = [k.transpose(1, 2) for k in [query_layer, key_layer, value_layer]]
-
-        # apply relative positional encoding (rotary embedding)
-        if rotary_pos_emb is not None:
-            query_layer = apply_rotary_pos_emb(query_layer, rotary_pos_emb)
-            key_layer = apply_rotary_pos_emb(key_layer, rotary_pos_emb)
-
-        # adjust key and value for inference
-        if kv_cache is not None:
-            cache_k, cache_v = kv_cache
-            key_layer = torch.cat((cache_k, key_layer), dim=2)
-            value_layer = torch.cat((cache_v, value_layer), dim=2)
-        if use_cache:
-            if kv_cache is None:
-                kv_cache = torch.cat((key_layer.unsqueeze(0).unsqueeze(0), value_layer.unsqueeze(0).unsqueeze(0)),
-                                     dim=1)
-            else:
-                kv_cache = (key_layer, value_layer)
-        else:
-            kv_cache = None
-
-        if self.multi_query_attention:
-            key_layer = key_layer.unsqueeze(2)
-            key_layer = key_layer.expand(
-                -1, -1, self.num_attention_heads_per_partition // self.num_multi_query_groups_per_partition, -1, -1
-            )
-            key_layer = key_layer.contiguous().view(
-                key_layer.size()[:1] + (self.num_attention_heads_per_partition,) + key_layer.size()[3:]
-            )
-            value_layer = value_layer.unsqueeze(2)
-            value_layer = value_layer.expand(
-                -1, -1, self.num_attention_heads_per_partition // self.num_multi_query_groups_per_partition, -1, -1
-            )
-            value_layer = value_layer.contiguous().view(
-                value_layer.size()[:1] + (self.num_attention_heads_per_partition,) + value_layer.size()[3:]
-            )
-
-        # ==================================
-        # core attention computation
-        # ==================================
-
-        context_layer = self.core_attention(query_layer, key_layer, value_layer, attention_mask)
-
-        # =================
-        # Output. [sq, b, h]
-        # =================
-
-        output = self.dense(context_layer)
-
-        return output, kv_cache
-
-
-def _config_to_kwargs(args):
-    common_kwargs = {
-        "dtype": args.torch_dtype,
-    }
-    return common_kwargs
-
-
-class MLP(torch.nn.Module):
-    """MLP.
-
-    MLP will take the input with h hidden state, project it to 4*h
-    hidden dimension, perform nonlinear transformation, and project the
-    state back into h hidden dimension.
-    """
-
-    def __init__(self, config: ChatGLMConfig, device=None):
-        super(MLP, self).__init__()
-
-        self.add_bias = config.add_bias_linear
-
-        # Project to 4h. If using swiglu double the output width, see https://arxiv.org/pdf/2002.05202.pdf
-        self.dense_h_to_4h = nn.Linear(
-            config.hidden_size,
-            config.ffn_hidden_size * 2,
-            bias=self.add_bias,
-            device=device,
-            **_config_to_kwargs(config)
-        )
-
-        def swiglu(x):
-            x = torch.chunk(x, 2, dim=-1)
-            return F.silu(x[0]) * x[1]
-
-        self.activation_func = swiglu
-
-        # Project back to h.
-        self.dense_4h_to_h = nn.Linear(
-            config.ffn_hidden_size,
-            config.hidden_size,
-            bias=self.add_bias,
-            device=device,
-            **_config_to_kwargs(config)
-        )
-
-    def forward(self, hidden_states):
-        # [s, b, 4hp]
-        intermediate_parallel = self.dense_h_to_4h(hidden_states)
-        intermediate_parallel = self.activation_func(intermediate_parallel)
-        # [s, b, h]
-        output = self.dense_4h_to_h(intermediate_parallel)
-        return output
-
-
-class GLMBlock(torch.nn.Module):
-    """A single transformer layer.
-
-    Transformer layer takes input with size [s, b, h] and returns an
-    output of the same size.
-    """
-
-    def __init__(self, config: ChatGLMConfig, layer_number, device=None):
-        super(GLMBlock, self).__init__()
-        self.layer_number = layer_number
-
-        self.apply_residual_connection_post_layernorm = config.apply_residual_connection_post_layernorm
-
-        self.fp32_residual_connection = config.fp32_residual_connection
-
-        LayerNormFunc = RMSNorm if config.rmsnorm else LayerNorm
-        # Layernorm on the input data.
-        self.input_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device,
-                                             dtype=config.torch_dtype)
-
-        # Self attention.
-        self.self_attention = SelfAttention(config, layer_number, device=device)
-        self.hidden_dropout = config.hidden_dropout
-
-        # Layernorm on the attention output
-        self.post_attention_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device,
-                                                      dtype=config.torch_dtype)
-
-        # MLP
-        self.mlp = MLP(config, device=device)
-
-    def forward(
-            self, hidden_states, attention_mask, rotary_pos_emb, kv_cache=None, use_cache=True,
-    ):
-        # hidden_states: [s, b, h]
-
-        # Layer norm at the beginning of the transformer layer.
-        layernorm_output = self.input_layernorm(hidden_states)
-        # Self attention.
-        attention_output, kv_cache = self.self_attention(
-            layernorm_output,
-            attention_mask,
-            rotary_pos_emb,
-            kv_cache=kv_cache,
-            use_cache=use_cache
-        )
-
-        # Residual connection.
-        if self.apply_residual_connection_post_layernorm:
-            residual = layernorm_output
-        else:
-            residual = hidden_states
-
-        layernorm_input = torch.nn.functional.dropout(attention_output, p=self.hidden_dropout, training=self.training)
-        layernorm_input = residual + layernorm_input
-
-        # Layer norm post the self attention.
-        layernorm_output = self.post_attention_layernorm(layernorm_input)
-
-        # MLP.
-        mlp_output = self.mlp(layernorm_output)
-
-        # Second residual connection.
-        if self.apply_residual_connection_post_layernorm:
-            residual = layernorm_output
-        else:
-            residual = layernorm_input
-
-        output = torch.nn.functional.dropout(mlp_output, p=self.hidden_dropout, training=self.training)
-        output = residual + output
-
-        return output, kv_cache
-
-
-class GLMTransformer(torch.nn.Module):
-    """Transformer class."""
-
-    def __init__(self, config: ChatGLMConfig, device=None):
-        super(GLMTransformer, self).__init__()
-
-        self.fp32_residual_connection = config.fp32_residual_connection
-        self.post_layer_norm = config.post_layer_norm
-
-        # Number of layers.
-        self.num_layers = config.num_layers
-
-        # Transformer layers.
-        def build_layer(layer_number):
-            return GLMBlock(config, layer_number, device=device)
-
-        self.layers = torch.nn.ModuleList([build_layer(i + 1) for i in range(self.num_layers)])
-
-        if self.post_layer_norm:
-            LayerNormFunc = RMSNorm if config.rmsnorm else LayerNorm
-            # Final layer norm before output.
-            self.final_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device,
-                                                 dtype=config.torch_dtype)
-
-        self.gradient_checkpointing = False
-
-    def _get_layer(self, layer_number):
-        return self.layers[layer_number]
-
-    def forward(
-            self, hidden_states, attention_mask, rotary_pos_emb, kv_caches=None,
-            use_cache: Optional[bool] = True,
-            output_hidden_states: Optional[bool] = False,
-    ):
-        if not kv_caches:
-            kv_caches = [None for _ in range(self.num_layers)]
-        presents = () if use_cache else None
-        if self.gradient_checkpointing and self.training:
-            if use_cache:
-                logger.warning_once(
-                    "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
-                )
-                use_cache = False
-
-        all_self_attentions = None
-        all_hidden_states = () if output_hidden_states else None
-        for index in range(self.num_layers):
-            if output_hidden_states:
-                all_hidden_states = all_hidden_states + (hidden_states,)
-
-            layer = self._get_layer(index)
-            if self.gradient_checkpointing and self.training:
-                layer_ret = torch.utils.checkpoint.checkpoint(
-                    layer,
-                    hidden_states,
-                    attention_mask,
-                    rotary_pos_emb,
-                    kv_caches[index],
-                    use_cache,
-                    use_reentrant=False
-                )
-            else:
-                layer_ret = layer(
-                    hidden_states,
-                    attention_mask,
-                    rotary_pos_emb,
-                    kv_cache=kv_caches[index],
-                    use_cache=use_cache
-                )
-            hidden_states, kv_cache = layer_ret
-            if use_cache:
-                # token by token decoding, use tuple format
-                if kv_caches[0] is not None:
-                    presents = presents + (kv_cache,)
-                # prefilling in decoding, use tensor format to save cuda memory
-                else:
-                    if len(presents) == 0:
-                        presents = kv_cache
-                    else:
-                        presents = torch.cat((presents, kv_cache.to(presents.device)), dim=0)
-
-        if output_hidden_states:
-            all_hidden_states = all_hidden_states + (hidden_states,)
-
-        # Final layer norm.
-        if self.post_layer_norm:
-            hidden_states = self.final_layernorm(hidden_states)
-
-        return hidden_states, presents, all_hidden_states, all_self_attentions
-
-
-class ChatGLMPreTrainedModel(PreTrainedModel):
-    """
-    An abstract class to handle weights initialization and
-    a simple interface for downloading and loading pretrained models.
-    """
-
-    is_parallelizable = False
-    supports_gradient_checkpointing = True
-    config_class = ChatGLMConfig
-    base_model_prefix = "transformer"
-    _no_split_modules = ["GLMBlock"]
-    _supports_flash_attn_2 = True
-    _supports_sdpa = True
-
-    def _init_weights(self, module: nn.Module):
-        """Initialize the weights."""
-        return
-
-    def get_masks(self, input_ids, past_key_values, padding_mask=None):
-        if self.config._attn_implementation == "flash_attention_2":
-            if padding_mask is not None and not padding_mask.all():
-                return padding_mask
-            return None
-        batch_size, seq_length = input_ids.shape
-        full_attention_mask = torch.ones(batch_size, seq_length, seq_length, device=input_ids.device)
-        full_attention_mask.tril_()
-        past_length = 0
-        if past_key_values:
-            past_length = past_key_values[0][0].shape[2]
-        if past_length:
-            full_attention_mask = torch.cat((torch.ones(batch_size, seq_length, past_length,
-                                                        device=input_ids.device), full_attention_mask), dim=-1)
-        if padding_mask is not None:
-            full_attention_mask = full_attention_mask * padding_mask.unsqueeze(1)
-        if not past_length and padding_mask is not None:
-            full_attention_mask -= padding_mask.unsqueeze(-1) - 1
-        full_attention_mask = (full_attention_mask < 0.5).bool()
-        full_attention_mask.unsqueeze_(1)
-        return full_attention_mask
-
-    def get_position_ids(self, input_ids, device):
-        batch_size, seq_length = input_ids.shape
-        position_ids = torch.arange(seq_length, dtype=torch.long, device=device).unsqueeze(0).repeat(batch_size, 1)
-        return position_ids
-
-class Embedding(torch.nn.Module):
-    """Language model embeddings."""
-
-    def __init__(self, config: ChatGLMConfig, device=None):
-        super(Embedding, self).__init__()
-
-        self.hidden_size = config.hidden_size
-        # Word embeddings (parallel).
-        self.word_embeddings = nn.Embedding(
-            config.padded_vocab_size,
-            self.hidden_size,
-            dtype=config.torch_dtype,
-            device=device
-        )
-        self.fp32_residual_connection = config.fp32_residual_connection
-
-    def forward(self, input_ids):
-        # Embeddings.
-        words_embeddings = self.word_embeddings(input_ids)
-        embeddings = words_embeddings
-        # If the input flag for fp32 residual connection is set, convert for float.
-        if self.fp32_residual_connection:
-            embeddings = embeddings.float()
-        return embeddings
-
-
-class ChatGLMModel(ChatGLMPreTrainedModel):
-    def __init__(self, config: ChatGLMConfig, device=None, empty_init=True):
-        super().__init__(config)
-        if empty_init:
-            init_method = skip_init
-        else:
-            init_method = default_init
-        init_kwargs = {}
-        if device is not None:
-            init_kwargs["device"] = device
-        self.embedding = init_method(Embedding, config, **init_kwargs)
-        self.num_layers = config.num_layers
-        self.multi_query_group_num = config.multi_query_group_num
-        self.kv_channels = config.kv_channels
-
-        # Rotary positional embeddings
-        self.seq_length = config.seq_length
-        rotary_dim = (
-            config.hidden_size // config.num_attention_heads if config.kv_channels is None else config.kv_channels
-        )
-
-        self.rotary_pos_emb = RotaryEmbedding(rotary_dim // 2, rope_ratio=config.rope_ratio,
-                                              original_impl=config.original_rope,
-                                              device=device, dtype=config.torch_dtype)
-        self.encoder = init_method(GLMTransformer, config, **init_kwargs)
-        self.output_layer = init_method(nn.Linear, config.hidden_size, config.padded_vocab_size, bias=False,
-                                        dtype=config.torch_dtype, **init_kwargs)
-
-    def get_input_embeddings(self):
-        return self.embedding.word_embeddings
-
-    def set_input_embeddings(self, value):
-        self.embedding.word_embeddings = value
-
-    def forward(
-            self,
-            input_ids,
-            position_ids: Optional[torch.Tensor] = None,
-            attention_mask: Optional[torch.BoolTensor] = None,
-            full_attention_mask: Optional[torch.BoolTensor] = None,
-            past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None,
-            inputs_embeds: Optional[torch.Tensor] = None,
-            use_cache: Optional[bool] = None,
-            output_attentions: Optional[bool] = None,
-            output_hidden_states: Optional[bool] = None,
-            return_dict: Optional[bool] = None,
-    ):
-        output_hidden_states = (
-            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
-        )
-        use_cache = use_cache if use_cache is not None else self.config.use_cache
-        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
-
-        batch_size, seq_length = input_ids.shape
-
-        if inputs_embeds is None:
-            inputs_embeds = self.embedding(input_ids)
-
-        if full_attention_mask is None:
-            if (attention_mask is not None and not attention_mask.all()) or (past_key_values and seq_length != 1):
-                full_attention_mask = self.get_masks(input_ids, past_key_values, padding_mask=attention_mask)
-
-        # Rotary positional embeddings
-        rotary_pos_emb = self.rotary_pos_emb(self.seq_length)
-        if position_ids is not None:
-            rotary_pos_emb = rotary_pos_emb[position_ids]
-        else:
-            rotary_pos_emb = rotary_pos_emb[None, :seq_length]
-
-        # Run encoder.
-        hidden_states, presents, all_hidden_states, all_self_attentions = self.encoder(
-            inputs_embeds, full_attention_mask, rotary_pos_emb=rotary_pos_emb,
-            kv_caches=past_key_values, use_cache=use_cache, output_hidden_states=output_hidden_states
-        )
-        if presents is not None and type(presents) is torch.Tensor:
-            presents = presents.split(1, dim=0)
-            presents = list(presents)
-            presents = [list(x.squeeze(0).split(1, dim=0)) for x in presents]
-            presents = [tuple([x.squeeze(0) for x in y]) for y in presents]
-            presents = tuple(presents)
-
-        if not return_dict:
-            return tuple(v for v in [hidden_states, presents, all_hidden_states, all_self_attentions] if v is not None)
-
-        return BaseModelOutputWithPast(
-            last_hidden_state=hidden_states,
-            past_key_values=presents,
-            hidden_states=all_hidden_states,
-            attentions=all_self_attentions,
-        )
-
-
-class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
-    def __init__(self, config: ChatGLMConfig, empty_init=True, device=None):
-        super().__init__(config)
-
-        self.max_sequence_length = config.max_length
-        self.transformer = ChatGLMModel(config, empty_init=empty_init, device=device)
-        self.config = config
-
-    def _update_model_kwargs_for_generation(
-            self,
-            outputs: ModelOutput,
-            model_kwargs: Dict[str, Any],
-            is_encoder_decoder: bool = False,
-    ) -> Dict[str, Any]:
-        # update past_key_values
-        cache_name, cache = self._extract_past_from_model_output(outputs)
-        model_kwargs[cache_name] = cache
-
-        # update attention mask
-        if "attention_mask" in model_kwargs:
-            attention_mask = model_kwargs["attention_mask"]
-            model_kwargs["attention_mask"] = torch.cat(
-                [attention_mask, attention_mask.new_ones((attention_mask.shape[0], 1))], dim=-1
-            )
-
-        # update position ids
-        if "position_ids" in model_kwargs:
-            position_ids = model_kwargs["position_ids"]
-            new_position_id = position_ids[..., -1:].clone()
-            new_position_id += 1
-            model_kwargs["position_ids"] = torch.cat(
-                [position_ids, new_position_id], dim=-1
-            )
-
-        model_kwargs["is_first_forward"] = False
-        return model_kwargs
-
-    def prepare_inputs_for_generation(
-            self,
-            input_ids: torch.LongTensor,
-            past_key_values: Optional[torch.Tensor] = None,
-            attention_mask: Optional[torch.Tensor] = None,
-            position_ids: Optional[torch.Tensor] = None,
-            use_cache: Optional[bool] = None,
-            is_first_forward: bool = True,
-            **kwargs
-    ) -> dict:
-        # only last token for input_ids if past is not None
-        if position_ids is None:
-            position_ids = self.get_position_ids(input_ids, device=input_ids.device)
-        if not is_first_forward:
-            if past_key_values is not None:
-                position_ids = position_ids[..., -1:]
-                input_ids = input_ids[:, -1:]
-        return {
-            "input_ids": input_ids,
-            "past_key_values": past_key_values,
-            "position_ids": position_ids,
-            "attention_mask": attention_mask,
-            "return_last_logit": True,
-            "use_cache": use_cache
-        }
-
-    def forward(
-            self,
-            input_ids: Optional[torch.Tensor] = None,
-            position_ids: Optional[torch.Tensor] = None,
-            attention_mask: Optional[torch.Tensor] = None,
-            past_key_values: Optional[Tuple[torch.FloatTensor]] = None,
-            inputs_embeds: Optional[torch.Tensor] = None,
-            labels: Optional[torch.Tensor] = None,
-            use_cache: Optional[bool] = None,
-            output_attentions: Optional[bool] = None,
-            output_hidden_states: Optional[bool] = None,
-            return_dict: Optional[bool] = None,
-            return_last_logit: Optional[bool] = False,
-    ):
-        use_cache = use_cache if use_cache is not None else self.config.use_cache
-        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
-
-        transformer_outputs = self.transformer(
-            input_ids=input_ids,
-            position_ids=position_ids,
-            attention_mask=attention_mask,
-            past_key_values=past_key_values,
-            inputs_embeds=inputs_embeds,
-            use_cache=use_cache,
-            output_hidden_states=output_hidden_states,
-            return_dict=return_dict,
-        )
-
-        hidden_states = transformer_outputs[0]
-        if return_last_logit:
-            hidden_states = hidden_states[:, -1:]
-        lm_logits = self.transformer.output_layer(hidden_states)
-
-        loss = None
-        if labels is not None:
-            lm_logits = lm_logits.to(torch.float32)
-
-            # Shift so that tokens < n predict n
-            shift_logits = lm_logits[..., :-1, :].contiguous()
-            shift_labels = labels[..., 1:].contiguous()
-            # Flatten the tokens
-            loss_fct = CrossEntropyLoss(ignore_index=-100)
-            loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))
-
-            lm_logits = lm_logits.to(hidden_states.dtype)
-            loss = loss.to(hidden_states.dtype)
-
-        if not return_dict:
-            output = (lm_logits,) + transformer_outputs[1:]
-            return ((loss,) + output) if loss is not None else output
-
-        return CausalLMOutputWithPast(
-            loss=loss,
-            logits=lm_logits,
-            past_key_values=transformer_outputs.past_key_values,
-            hidden_states=transformer_outputs.hidden_states,
-            attentions=transformer_outputs.attentions,
-        )
-
-    @staticmethod
-    def _reorder_cache(
-            past: Tuple[Tuple[torch.Tensor, torch.Tensor], ...], beam_idx: torch.LongTensor
-    ) -> Tuple[Tuple[torch.Tensor, torch.Tensor], ...]:
-        """
-        This function is used to re-order the `past_key_values` cache if [`~PreTrainedModel.beam_search`] or
-        [`~PreTrainedModel.beam_sample`] is called. This is required to match `past_key_values` with the correct
-        beam_idx at every generation step.
-
-        Output shares the same memory storage as `past`.
-        """
-        return tuple(
-            (
-                layer_past[0].index_select(0, beam_idx.to(layer_past[0].device)),
-                layer_past[1].index_select(0, beam_idx.to(layer_past[1].device)),
-            )
-            for layer_past in past
-        )
-
-class ChatGLMForSequenceClassification(ChatGLMPreTrainedModel):
-    def __init__(self, config: ChatGLMConfig, empty_init=True, device=None):
-        super().__init__(config)
-
-        self.num_labels = config.num_labels
-        self.transformer = ChatGLMModel(config, empty_init=empty_init, device=device)
-
-        self.classifier_head = nn.Linear(config.hidden_size, config.num_labels, bias=True, dtype=config.torch_dtype)
-        if config.classifier_dropout is not None:
-            self.dropout = nn.Dropout(config.classifier_dropout)
-        else:
-            self.dropout = None
-        self.config = config
-
-    def forward(
-            self,
-            input_ids: Optional[torch.LongTensor] = None,
-            position_ids: Optional[torch.LongTensor] = None,
-            attention_mask: Optional[torch.Tensor] = None,
-            full_attention_mask: Optional[torch.Tensor] = None,
-            past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None,
-            inputs_embeds: Optional[torch.LongTensor] = None,
-            labels: Optional[torch.LongTensor] = None,
-            use_cache: Optional[bool] = None,
-            output_attentions: Optional[bool] = None,
-            output_hidden_states: Optional[bool] = None,
-            return_dict: Optional[bool] = None,
-    ) -> Union[Tuple[torch.Tensor, ...], SequenceClassifierOutputWithPast]:
-        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
-
-        transformer_outputs = self.transformer(
-            input_ids=input_ids,
-            position_ids=position_ids,
-            attention_mask=attention_mask,
-            full_attention_mask=full_attention_mask,
-            past_key_values=past_key_values,
-            inputs_embeds=inputs_embeds,
-            use_cache=use_cache,
-            output_attentions=output_attentions,
-            output_hidden_states=output_hidden_states,
-            return_dict=return_dict,
-        )
-
-        hidden_states = transformer_outputs[0]
-        pooled_hidden_states = hidden_states[:, -1]
-        if self.dropout is not None:
-            pooled_hidden_states = self.dropout(pooled_hidden_states)
-        logits = self.classifier_head(pooled_hidden_states)
-
-        loss = None
-        if labels is not None:
-            if self.config.problem_type is None:
-                if self.num_labels == 1:
-                    self.config.problem_type = "regression"
-                elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
-                    self.config.problem_type = "single_label_classification"
-                else:
-                    self.config.problem_type = "multi_label_classification"
-
-            if self.config.problem_type == "regression":
-                loss_fct = MSELoss()
-                if self.num_labels == 1:
-                    loss = loss_fct(logits.squeeze().float(), labels.squeeze())
-                else:
-                    loss = loss_fct(logits.float(), labels)
-            elif self.config.problem_type == "single_label_classification":
-                loss_fct = CrossEntropyLoss()
-                loss = loss_fct(logits.view(-1, self.num_labels).float(), labels.view(-1))
-            elif self.config.problem_type == "multi_label_classification":
-                loss_fct = BCEWithLogitsLoss()
-                loss = loss_fct(logits.float(), labels.view(-1, self.num_labels))
-
-        if not return_dict:
-            output = (logits,) + transformer_outputs[1:]
-            return ((loss,) + output) if loss is not None else output
-
-        return SequenceClassifierOutputWithPast(
-            loss=loss,
-            logits=logits,
-            past_key_values=transformer_outputs.past_key_values,
-            hidden_states=transformer_outputs.hidden_states,
-            attentions=transformer_outputs.attentions,
-        )

special_tokens_map.json

@@ -1,32 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|endoftext|>",
-    "[MASK]",
-    "[gMASK]",
-    "[sMASK]",
-    "<sop>",
-    "<eop>",
-    "<|system|>",
-    "<|user|>",
-    "<|assistant|>",
-    "<|observation|>",
-    "<|begin_of_image|>",
-    "<|end_of_image|>",
-    "<|begin_of_video|>",
-    "<|end_of_video|>"
-  ],
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenization_chatglm.py

@@ -1,324 +0,0 @@
-import regex as re
-import base64
-import os
-import json
-import tiktoken
-from torch import TensorType
-from typing import List, Optional, Union, Dict, Any
-from transformers import PreTrainedTokenizer
-from transformers.utils import logging, PaddingStrategy
-from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
-
-
-class ChatGLM4Tokenizer(PreTrainedTokenizer):
-    vocab_files_names = {"vocab_file": "tokenizer.model"}
-    model_input_names = ["input_ids", "attention_mask", "position_ids"]
-
-    def __init__(
-            self,
-            vocab_file,
-            padding_side="left",
-            clean_up_tokenization_spaces=False,
-            encode_special_tokens=False,
-            **kwargs
-    ):
-        self.name = "GLM4Tokenizer"
-        self.vocab_file = vocab_file
-        pat_str = "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
-        self.pat_str = re.compile(pat_str)
-        self.encode_special_tokens = encode_special_tokens
-
-        mergeable_ranks = {}
-        with open(vocab_file) as f:
-            for line in f:
-                token, rank = line.strip().split()
-                rank = int(rank)
-                token = base64.b64decode(token)
-                mergeable_ranks[token] = rank
-
-        self.mergeable_ranks = mergeable_ranks
-
-        self.tokenizer = tiktoken.Encoding(
-            name="my_tokenizer",
-            pat_str=pat_str,
-            mergeable_ranks=mergeable_ranks,
-            special_tokens={}
-        )
-        self.decoder = {rank: token for token, rank in mergeable_ranks.items()}
-        self.n_words = len(self.decoder)
-
-        super().__init__(
-            padding_side=padding_side,
-            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
-            **kwargs
-        )
-
-    @property
-    def vocab_size(self):
-        return self.n_words
-
-    def get_vocab(self):
-        """ Returns vocab as a dict """
-        vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
-        vocab.update(self.added_tokens_encoder)
-        return vocab
-
-    def convert_tokens_to_string(self, tokens: List[Union[bytes, str, int]]) -> str:
-        """
-        Converts a sequence of tokens in a single string.
-        """
-        text = ""
-        temp = b""
-        for t in tokens:
-            if isinstance(t, int):
-                t = chr(t)
-            if isinstance(t, str):
-                if temp:
-                    text += temp.decode("utf-8", errors="replace")
-            elif isinstance(t, bytes):
-                temp += t
-            else:
-                raise TypeError("token should only be of type int, bytes or str")
-        if temp:
-            text += temp.decode("utf-8", errors="replace")
-        return text
-
-    def _tokenize(self, text, **kwargs):
-        tokens = []
-        ids = self.tokenizer.encode(text)
-        for t in ids:
-            tokens.append(self.decoder[t])
-        return tokens
-
-    def _convert_token_to_id(self, token):
-        """ Converts a token (str) in an id using the vocab. """
-        return self.mergeable_ranks[token]
-
-    def _convert_id_to_token(self, index):
-        """Converts an index (integer) in a token (str) using the vocab."""
-        return self.decoder.get(index, "")
-
-    def save_vocabulary(self, save_directory, filename_prefix=None):
-        """
-        Save the vocabulary and special tokens file to a directory.
-
-        Args:
-            save_directory (`str`):
-                The directory in which to save the vocabulary.
-            filename_prefix (`str`, *optional*):
-                An optional prefix to add to the named of the saved files.
-
-        Returns:
-            `Tuple(str)`: Paths to the files saved.
-        """
-        if os.path.isdir(save_directory):
-            vocab_file = os.path.join(
-                save_directory, self.vocab_files_names["vocab_file"]
-            )
-        else:
-            vocab_file = save_directory
-
-        with open(self.vocab_file, 'rb') as fin:
-            proto_str = fin.read()
-
-        with open(vocab_file, "wb") as writer:
-            writer.write(proto_str)
-
-        return (vocab_file,)
-
-    def get_prefix_tokens(self):
-        prefix_tokens = [self.convert_tokens_to_ids("[gMASK]"), self.convert_tokens_to_ids("<sop>")]
-        return prefix_tokens
-
-    def build_single_message(self, role, metadata, message, tokenize=True):
-        assert role in ["system", "user", "assistant", "observation"], role
-        if tokenize:
-            role_tokens = [self.convert_tokens_to_ids(f"<|{role}|>")] + self.tokenizer.encode(f"{metadata}\n",
-                                                                                              disallowed_special=())
-            message_tokens = self.tokenizer.encode(message, disallowed_special=())
-            tokens = role_tokens + message_tokens
-            return tokens
-        else:
-            return str(f"<|{role}|>{metadata}\n{message}")
-
-    def apply_chat_template(
-            self,
-            conversation: Union[List[Dict[str, str]], List[List[Dict[str, str]]], "Conversation"],
-            add_generation_prompt: bool = False,
-            tokenize: bool = True,
-            padding: bool = False,
-            truncation: bool = False,
-            max_length: Optional[int] = None,
-            return_tensors: Optional[Union[str, TensorType]] = None,
-            return_dict: bool = False,
-            tokenizer_kwargs: Optional[Dict[str, Any]] = None,
-            add_special_tokens: bool = True,
-            **kwargs,
-    ) -> Union[str, List[int], List[str], List[List[int]], BatchEncoding]:
-
-        if return_dict and not tokenize:
-            raise ValueError(
-                "`return_dict=True` is incompatible with `tokenize=False`, because there is no dict "
-                "of tokenizer outputs to return."
-            )
-
-        def handle_single_conversation(conversation):
-            input_ids = self.get_prefix_tokens() if add_special_tokens else []
-            input_message = "[gMASK]<sop>" if add_special_tokens else ""
-            for item in conversation:
-                if item.get("tools"):
-                    tools = item["tools"]
-                    content = "你是一个名为 GhatGLM 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的，你的任务是针对用户的问题和要求提供适当的答复和支持。"
-                    content += "\n\n# 可用工具"
-                    for tool in tools:
-                        if tool["type"] == "function":
-                            function = tool["function"]
-                            content += f"\n\n## {function['name']}\n\n{json.dumps(function, ensure_ascii=False, indent=4)}"
-                            content += "\n在调用上述函数时，请使用 Json 格式表示调用的参数。"
-                        elif tool["type"] == "python":
-                            content += "\n\n## python\n\n当你向 `python` 发送包含 Python 代码的消息时，该代码将会在一个有状态的 Jupyter notebook 环境中执行。\n`python` 返回代码执行的输出，或在执行 60 秒后返回超时。\n`/mnt/data` 将会持久化存储你的文件。在此会话中，`python` 无法访问互联网。不要使用 `python` 进行任何网络请求或者在线 API 调用，这些在线内容的访问将不会成功。"
-                        elif tool["type"] == "simple_browser":
-                            content += "\n\n## simple_browser\n\n你可以使用 `simple_browser` 工具。该工具支持以下函数：\n`search(query: str, recency_days: int)`：使用搜索引擎进行查询并显示结果，可以使用 `recency_days` 参数控制搜索内容的时效性。\n`mclick(ids: list[int])`：获取一系列指定 id 的页面内容。每次调用时，须选择3-10个页面。选择多个角度的页面，同时尽可能选择可信任的信息来源。考虑到部分页面是无法加载的，你也可以多打开一些可能有用的页面而不用担心内容过多。\n`open_url(url: str)`：打开指定的 URL。\n\n使用 `【{引用 id}†{引用文本}】` 来引用内容。\n\n操作步骤：1. 使用 `search` 来获得信息列表; 2. 使用 `mclick` 来获取指定 ID 页面的内容; 3. 根据获得的内容进行回复。在回复中应当引用信息来源。\n 如果用户提供了 URL，也可以用 `open_url` 直接打开页面。\n如果初次搜索结果没有找到合适的信息，也可以再次使用 `search` 进行搜索。"
-                        elif tool["type"] == "cogview":
-                            content += "\n\n## cogview\n\n如果用户的请求中包含了对图像的描述，你可以使用 `cogview` 来生成图像并展示给用户。你需要向 `cogview` 发送图像描述，规则：\n- 发送给 `cogview` 的消息必须使用英语。用户的中文描述必须完全翻译为英语。\n- 应当尽可能详细地描述图像生成的需求，需求描述约 100 英文单词。\n- 保持用户原始描述的意图。不要虚构内容或者没见过的人物。\n- 如无特殊说明，所在地为中国，持有中国立场并遵循中国社会主义价值观。"
-                        else:
-                            raise NotImplementedError(f"Unknown tool type {tool['type']}")
-                    input = self.build_single_message("system", "", content, tokenize=tokenize)
-                    if tokenize:
-                        input_ids.extend(input)
-                    else:
-                        input_message += input
-                if item["content"]:
-                    input = self.build_single_message(
-                        item["role"],
-                        item.get("metadata", ""),
-                        item["content"],
-                        tokenize=tokenize
-                    )
-                    if tokenize:
-                        input_ids.extend(input)
-                    else:
-                        input_message += input
-            if add_generation_prompt:
-                if tokenize:
-                    input_ids.extend([self.convert_tokens_to_ids("<|assistant|>")])
-                else:
-                    input_message += "<|assistant|>"
-            return input_ids if tokenize else input_message
-
-        # Main logic to handle different conversation formats
-        if isinstance(conversation, list) and all(isinstance(i, dict) for i in conversation):
-            result = handle_single_conversation(conversation)
-        elif isinstance(conversation, list) and all(isinstance(i, list) for i in conversation):
-            result = [handle_single_conversation(c) for c in conversation]
-        elif hasattr(conversation, "messages"):
-            result = handle_single_conversation(conversation.messages)
-        else:
-            raise ValueError("Invalid conversation format")
-
-        if tokenize:
-            output = self.batch_encode_plus(
-                [result] if isinstance(result[0], int) else result,
-                padding=padding,
-                truncation=truncation,
-                max_length=max_length,
-                return_tensors=return_tensors,
-                is_split_into_words=True,
-                add_special_tokens=False
-            )
-            if return_dict:
-                return output
-            else:
-                return output["input_ids"]
-        else:
-            return result
-
-
-    def build_inputs_with_special_tokens(
-            self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
-    ) -> List[int]:
-        """
-        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
-        adding special tokens. A BERT sequence has the following format:
-
-        - single sequence: `[CLS] X [SEP]`
-        - pair of sequences: `[CLS] A [SEP] B [SEP]`
-
-        Args:
-            token_ids_0 (`List[int]`):
-                List of IDs to which the special tokens will be added.
-            token_ids_1 (`List[int]`, *optional*):
-                Optional second list of IDs for sequence pairs.
-
-        Returns:
-            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
-        """
-        prefix_tokens = self.get_prefix_tokens()
-        token_ids_0 = prefix_tokens + token_ids_0
-        if token_ids_1 is not None:
-            token_ids_0 = token_ids_0 + token_ids_1 + [self.convert_tokens_to_ids("<eos>")]
-        return token_ids_0
-
-    def _pad(
-            self,
-            encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
-            max_length: Optional[int] = None,
-            padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
-            pad_to_multiple_of: Optional[int] = None,
-            padding_side: Optional[str] = None,
-            return_attention_mask: Optional[bool] = None,
-    ) -> dict:
-        """
-        Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
-
-        Args:
-            encoded_inputs:
-                Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
-            max_length: maximum length of the returned list and optionally padding length (see below).
-                Will truncate by taking into account the special tokens.
-            padding_strategy: PaddingStrategy to use for padding.
-
-                - PaddingStrategy.LONGEST Pad to the longest sequence in the batch
-                - PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
-                - PaddingStrategy.DO_NOT_PAD: Do not pad
-                The tokenizer padding sides are defined in self.padding_side:
-
-                    - 'left': pads on the left of the sequences
-                    - 'right': pads on the right of the sequences
-            pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
-                This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
-                `>= 7.5` (Volta).
-            return_attention_mask:
-                (optional) Set to False to avoid returning attention mask (default: set to model specifics)
-        """
-        # Load from model defaults
-        assert self.padding_side == "left"
-
-        required_input = encoded_inputs[self.model_input_names[0]]
-        seq_length = len(required_input)
-
-        if padding_strategy == PaddingStrategy.LONGEST:
-            max_length = len(required_input)
-
-        if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
-            max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
-
-        needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
-
-        # Initialize attention mask if not present.
-        if "attention_mask" not in encoded_inputs:
-            encoded_inputs["attention_mask"] = [1] * seq_length
-
-        if "position_ids" not in encoded_inputs:
-            encoded_inputs["position_ids"] = list(range(seq_length))
-
-        if needs_to_be_padded:
-            difference = max_length - len(required_input)
-
-            if "attention_mask" in encoded_inputs:
-                encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
-            if "position_ids" in encoded_inputs:
-                encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
-            encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
-
-        return encoded_inputs

tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5a493598071550244b2ee7f26118f3edec2150b9dfa967929a99052ac83fe716
-size 2623634

tokenizer_config.json

@@ -129,12 +129,6 @@
     "<|begin_of_video|>",
     "<|end_of_video|>"
   ],
-  "auto_map": {
-    "AutoTokenizer": [
-      "tokenization_chatglm.ChatGLM4Tokenizer",
-      null
-    ]
-  },
   "clean_up_tokenization_spaces": false,
   "do_lower_case": false,
   "eos_token": "<|endoftext|>",