Initial commit

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright Zhengxiao Du
+
+   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.

MODEL_LICENSE

@@ -0,0 +1,65 @@
+The CodeGeeX2-6B License
+
+1. 定义
+
+“许可方”是指分发其软件的 CodeGeeX2-6B 模型团队。
+
+“软件”是指根据本许可提供的 CodeGeeX2-6B 模型参数。
+
+2. 许可授予
+
+根据本许可的条款和条件，许可方特此授予您非排他性、全球性、不可转让、不可再许可、可撤销、免版税的版权许可。
+
+上述版权声明和本许可声明应包含在本软件的所有副本或重要部分中。
+
+3. 限制
+
+您不得出于任何军事或非法目的使用、复制、修改、合并、发布、分发、复制或创建本软件的全部或部分衍生作品。
+
+您不得利用本软件从事任何危害国家安全和国家统一、危害社会公共利益、侵犯人身权益的行为。
+
+4. 免责声明
+
+本软件“按原样”提供，不提供任何明示或暗示的保证，包括但不限于对适销性、特定用途的适用性和非侵权性的保证。 在任何情况下，作者或版权持有人均不对任何索赔、损害或其他责任负责，无论是在合同诉讼、侵权行为还是其他方面，由软件或软件的使用或其他交易引起、由软件引起或与之相关 软件。
+
+5. 责任限制
+
+除适用法律禁止的范围外，在任何情况下且根据任何法律理论，无论是基于侵权行为、疏忽、合同、责任或其他原因，任何许可方均不对您承担任何直接、间接、特殊、偶然、示范性、 或间接损害，或任何其他商业损失，即使许可人已被告知此类损害的可能性。
+
+6.争议解决
+
+本许可受中华人民共和国法律管辖并按其解释。 因本许可引起的或与本许可有关的任何争议应提交北京市海淀区人民法院。
+
+请注意，许可证可能会更新到更全面的版本。 有关许可和版权的任何问题，请通过 [email protected] 与我们联系。
+
+1. Definitions
+
+“Licensor” means the CodeGeeX2-6B Model Team that distributes its Software.
+
+“Software” means the CodeGeeX2-6B model parameters made available under this license.
+
+2. License Grant
+
+Subject to the terms and conditions of this License, the Licensor hereby grants to you a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable, royalty-free copyright license to use the Software.
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+3. Restriction
+
+You will not use, copy, modify, merge, publish, distribute, reproduce, or create derivative works of the Software, in whole or in part, for any military, or illegal purposes.
+
+You will not use the Software for any act that may undermine China's national security and national unity, harm the public interest of society, or infringe upon the rights and interests of human beings.
+
+4. Disclaimer
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+5. Limitation of Liability
+
+EXCEPT TO THE EXTENT PROHIBITED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER BASED IN TORT, NEGLIGENCE, CONTRACT, LIABILITY, OR OTHERWISE WILL ANY LICENSOR BE LIABLE TO YOU FOR ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES, OR ANY OTHER COMMERCIAL LOSSES, EVEN IF THE LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
+
+6. Dispute Resolution
+
+This license shall be governed and construed in accordance with the laws of People’s Republic of China. Any dispute arising from or in connection with this License shall be submitted to Haidian District People's Court in Beijing.
+
+Note that the license is subject to update to a more comprehensive version.  For any questions related to the license and copyright, please contact us at [email protected].

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "THUDM/codegeex2-6b",
+  "model_type": "chatglm",
+  "architectures": [
+    "ChatGLMModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration"
+  },
+  "add_bias_linear": false,
+  "add_qkv_bias": true,
+  "apply_query_key_layer_scaling": true,
+  "apply_residual_connection_post_layernorm": false,
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "ffn_hidden_size": 13696,
+  "fp32_residual_connection": false,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "interleaved_qkv": false,
+  "kv_channels": 128,
+  "layernorm_epsilon": 1e-05,
+  "multi_query_attention": true,
+  "multi_query_group_num": 2,
+  "num_attention_heads": 32,
+  "num_layers": 28,
+  "original_rope": true,
+  "padded_vocab_size": 65024,
+  "post_layer_norm": true,
+  "rmsnorm": true,
+  "rotary_percent": 0.5,
+  "seq_length": 8192,
+  "use_cache": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.27.1",
+  "tie_word_embeddings": false,
+  "eos_token_id": 2
+}

configuration_chatglm.py

@@ -0,0 +1,58 @@
+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,
+        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,
+        interleaved_qkv=False,
+        bias_dropout_fusion=True,
+        rotary_percent=1.0,
+        multi_query_attention=False,
+        multi_query_group_num=1,
+        apply_query_key_layer_scaling=True,
+        attention_softmax_in_fp32=True,
+        fp32_residual_connection=False,
+        quantization_bit=0,
+        **kwargs
+    ):
+        self.num_layers = num_layers
+        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.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.interleaved_qkv = interleaved_qkv
+        self.bias_dropout_fusion = bias_dropout_fusion
+        self.rotary_percent = rotary_percent
+        self.multi_query_attention = multi_query_attention
+        self.multi_query_group_num = multi_query_group_num
+        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
+        self.quantization_bit = quantization_bit
+        super().__init__(**kwargs)

modeling_chatglm.py

@@ -0,0 +1,1092 @@
+""" PyTorch ChatGLM model. """
+
+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
+from torch.nn.utils import skip_init
+from typing import Optional, Tuple, Union, List, Callable, Dict, Any
+
+from transformers.modeling_outputs import (
+    BaseModelOutputWithPast,
+    CausalLMOutputWithPast,
+)
+from transformers.modeling_utils import PreTrainedModel
+from transformers.utils import logging
+from transformers.generation.logits_process import LogitsProcessor
+from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig, ModelOutput
+
+from .configuration_chatglm import ChatGLMConfig
+
+# flags required to enable jit fusion kernels
+
+if sys.platform != 'darwin':
+    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-6B"
+_CONFIG_FOR_DOC = "ChatGLM6BConfig"
+
+CHATGLM_6B_PRETRAINED_MODEL_ARCHIVE_LIST = [
+    "THUDM/chatglm-6b",
+    # See all ChatGLM-6B models at https://huggingface.co/models?filter=chatglm
+]
+
+
+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[..., 5] = 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, original_impl=False, device=None, dtype=None):
+        super().__init__()
+        inv_freq = 1.0 / (10000 ** (torch.arange(0, dim, 2, device=device, dtype=dtype) / dim))
+        self.register_buffer("inv_freq", inv_freq)
+        self.dim = dim
+        self.original_impl = original_impl
+
+    def forward_original_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.
+        """
+        # $\Theta = {\theta_i = 10000^{\frac{2(i-1)}{d}}, i \in [1, 2, ..., \frac{d}{2}]}$
+        theta = 1.0 / (base ** (torch.arange(0, n_elem, 2, dtype=dtype, device=device) / n_elem))
+
+        # Create position indexes `[0, 1, ..., seq_len - 1]`
+        seq_idx = torch.arange(seq_len, dtype=dtype, 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):
+        if self.original_impl:
+            return self.forward_original_impl(
+                max_seq_len, self.dim, dtype=self.inv_freq.dtype, device=self.inv_freq.device
+            )
+
+
+@torch.jit.script
+def apply_rotary_pos_emb_original(x: torch.Tensor, rope_cache: torch.Tensor) -> torch.Tensor:
+    # x: [sq, b, np, hn]
+    sq, b, np, 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(sq, -1, np, rot_dim // 2, 2)
+    rope_cache = rope_cache.view(sq, -1, 1, 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, input: torch.Tensor):
+        norm_x = torch.mean(input * input, dim=-1, keepdim=True)
+        x_normed = input * torch.rsqrt(norm_x + self.eps)
+        return self.weight * x_normed
+
+
+class CoreAttention(torch.nn.Module):
+    def __init__(self, config: ChatGLMConfig, layer_number):
+        super(CoreAttention, self).__init__()
+
+        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)
+
+        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):
+        pytorch_major_version = int(torch.__version__.split('.')[0])
+        if pytorch_major_version >= 2:
+            query_layer, key_layer, value_layer = [k.permute(1, 2, 0, 3) for k in [query_layer, key_layer, value_layer]]
+            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)
+            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)
+            context_layer = context_layer.permute(2, 0, 1, 3)
+            new_context_layer_shape = context_layer.size()[:-2] + (self.hidden_size_per_partition,)
+            context_layer = context_layer.reshape(*new_context_layer_shape)
+        else:
+            # Raw attention scores
+
+            # [b, np, sq, sk]
+            output_size = (query_layer.size(1), query_layer.size(2), query_layer.size(0), key_layer.size(0))
+
+            # [sq, b, np, hn] -> [sq, b * np, hn]
+            query_layer = query_layer.view(output_size[2], output_size[0] * output_size[1], -1)
+            # [sk, b, np, hn] -> [sk, b * np, hn]
+            key_layer = key_layer.view(output_size[3], output_size[0] * output_size[1], -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.transpose(0, 1),  # [b * np, sq, hn]
+                key_layer.transpose(0, 1).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)
+            # =========================
+            # Context layer. [sq, b, hp]
+            # =========================
+
+            # value_layer -> context layer.
+            # [sk, b, np, hn] --> [b, np, sq, hn]
+
+            # context layer shape: [b, np, sq, hn]
+            output_size = (value_layer.size(1), value_layer.size(2), query_layer.size(0), value_layer.size(3))
+            # change view [sk, b * np, hn]
+            value_layer = value_layer.view(value_layer.size(0), output_size[0] * output_size[1], -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.transpose(0, 1))
+            # change view [b, np, sq, hn]
+            context_layer = context_layer.view(*output_size)
+            # [b, np, sq, hn] --> [sq, b, np, hn]
+            context_layer = context_layer.permute(2, 0, 1, 3).contiguous()
+            # [sq, b, np, hn] --> [sq, b, hp]
+            new_context_layer_shape = context_layer.size()[:-2] + (self.hidden_size_per_partition,)
+            context_layer = context_layer.view(*new_context_layer_shape)
+
+        return context_layer
+
+
+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 = CoreAttention(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)
+                               )
+
+        self.interleaved_qkv = config.interleaved_qkv
+
+    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: [sq, b, h]
+
+        # =================================================
+        # Pre-allocate memory for key-values for inference.
+        # =================================================
+        # =====================
+        # Query, Key, and Value
+        # =====================
+
+        # Attention heads [sq, b, h] --> [sq, b, (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:
+            if self.interleaved_qkv:
+                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)
+
+            # [sq, b, np, 3 * hn] --> 3 [sq, b, np, hn]
+            (query_layer, key_layer, value_layer) = split_tensor_along_last_dim(mixed_x_layer, 3)
+
+            if not self.interleaved_qkv:
+                query_layer = query_layer.view(
+                    query_layer.size()[:-1] + (
+                        self.num_attention_heads_per_partition, self.hidden_size_per_attention_head)
+                ).contiguous()
+                key_layer = key_layer.view(
+                    key_layer.size()[:-1] + (
+                        self.num_attention_heads_per_partition, self.hidden_size_per_attention_head)
+                ).contiguous()
+                value_layer = value_layer.view(
+                    value_layer.size()[:-1] + (
+                        self.num_attention_heads_per_partition, self.hidden_size_per_attention_head)
+                ).contiguous()
+
+        # apply relative positional encoding (rotary embedding)
+        if rotary_pos_emb is not None:
+            query_layer = apply_rotary_pos_emb_original(query_layer, rotary_pos_emb)
+            key_layer = apply_rotary_pos_emb_original(key_layer, rotary_pos_emb)
+
+        # adjust key and value for inference
+        if use_cache:
+            if kv_cache is not None:
+                cache_k, cache_v = kv_cache
+                key_layer = torch.cat((cache_k, key_layer), dim=0)
+                value_layer = torch.cat((cache_v, value_layer), dim=0)
+            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, -1, self.num_attention_heads_per_partition // self.num_multi_query_groups_per_partition, -1
+            )
+            key_layer = key_layer.contiguous().view(
+                key_layer.size()[:2] + (self.num_attention_heads_per_partition, self.hidden_size_per_attention_head)
+            )
+            value_layer = value_layer.unsqueeze(-2)
+            value_layer = value_layer.expand(
+                -1, -1, -1, self.num_attention_heads_per_partition // self.num_multi_query_groups_per_partition, -1
+            )
+            value_layer = value_layer.contiguous().view(
+                value_layer.size()[:2] + (self.num_attention_heads_per_partition, self.hidden_size_per_attention_head)
+            )
+
+        # ==================================
+        # 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)
+
+    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
+        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)
+
+            hidden_states, kv_cache = layer(
+                hidden_states,
+                attention_mask,
+                rotary_pos_emb,
+                kv_cache=kv_caches[index],
+                use_cache=use_cache
+            )
+            if use_cache:
+                presents = presents + (kv_cache,)
+
+        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"]
+
+    def _init_weights(self, module: nn.Module):
+        """Initialize the weights."""
+        return
+
+    def get_masks(self, input_ids, past_key_values, padding_mask=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[0]
+        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
+
+    def _set_gradient_checkpointing(self, module, value=False):
+        if isinstance(module, ChatGLMModel):
+            module.gradient_checkpointing = value
+
+
+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
+        # Data format change to avoid explicit tranposes : [b s h] --> [s b h].
+        embeddings = embeddings.transpose(0, 1).contiguous()
+        # 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)
+
+        # 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
+        )
+
+        if config.rotary_percent < 1.0:
+            rotary_dim = int(rotary_dim * config.rotary_percent)
+
+        # partial rotary embeddings, which is better than full rotary
+        # Wang and Komatsuzaki et al
+        # https://github.com/kingoflolz/mesh-transformer-jax/
+        self.rotary_pos_emb = RotaryEmbedding(rotary_dim, 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)
+        self.gradient_checkpointing = False
+
+    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_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 and attention_mask is not None and not attention_mask.all():
+            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]
+        rotary_pos_emb = rotary_pos_emb.transpose(0, 1).contiguous()
+
+        # 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 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,
+        )
+
+    def quantize(self, weight_bit_width: int):
+        from .quantization import quantize
+        quantize(self.encoder, weight_bit_width)
+        return self
+
+
+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
+        self.quantized = False
+
+        if self.config.quantization_bit:
+            self.quantize(self.config.quantization_bit, empty_init=True)
+
+    def _update_model_kwargs_for_generation(
+            self,
+            outputs: ModelOutput,
+            model_kwargs: Dict[str, Any],
+            is_encoder_decoder: bool = False,
+            standardize_cache_format: bool = False,
+    ) -> Dict[str, Any]:
+        # update past_key_values
+        model_kwargs["past_key_values"] = self._extract_past_from_model_output(
+            outputs, standardize_cache_format=standardize_cache_format
+        )
+
+        # 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
+            )
+
+        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,
+            input_pos: int = None,
+            **kwargs
+    ) -> dict:
+        # only last token for input_ids if past is not None
+        if past_key_values is not None:
+            if position_ids is None:
+                position_ids = self.get_position_ids(input_ids, device=input_ids.device)
+            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
+        }
+
+    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,
+    ):
+        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]
+
+        lm_logits = self.transformer.output_layer(hidden_states)
+        lm_logits = lm_logits.transpose(0, 1).contiguous()
+
+        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(1, beam_idx.to(layer_past[0].device)),
+                layer_past[1].index_select(1, beam_idx.to(layer_past[1].device)),
+            )
+            for layer_past in past
+        )
+
+    def process_response(self, response):
+        response = response.strip()
+        response = response.replace("[[训练时间]]", "2023年")
+        return response
+
+    def build_inputs(self, tokenizer, query: str, history: List[Tuple[str, str]] = None):
+        prompt = ""
+        for i, (old_query, response) in enumerate(history):
+            prompt += "[Round {}]\n\n问：{}\n\n答：{}\n\n".format(i + 1, old_query, response)
+        prompt += "[Round {}]\n\n问：{}\n\n答：".format(len(history) + 1, query)
+        inputs = tokenizer([prompt], return_tensors="pt")
+        inputs = inputs.to(self.device)
+        return inputs
+
+    @torch.no_grad()
+    def chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, max_length: int = 2048, num_beams=1,
+             do_sample=True, top_p=0.8, temperature=0.8, logits_processor=None, **kwargs):
+        if history is None:
+            history = []
+        if logits_processor is None:
+            logits_processor = LogitsProcessorList()
+        logits_processor.append(InvalidScoreLogitsProcessor())
+        gen_kwargs = {"max_length": max_length, "num_beams": num_beams, "do_sample": do_sample, "top_p": top_p,
+                      "temperature": temperature, "logits_processor": logits_processor, **kwargs}
+        inputs = self.build_inputs(tokenizer, query, history=history)
+        outputs = self.generate(**inputs, **gen_kwargs)
+        outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):]
+        response = tokenizer.decode(outputs)
+        response = self.process_response(response)
+        history = history + [(query, response)]
+        return response, history
+
+    @torch.no_grad()
+    def stream_chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, max_length: int = 2048,
+                    do_sample=True, top_p=0.7, temperature=0.95, logits_processor=None, **kwargs):
+        if history is None:
+            history = []
+        if logits_processor is None:
+            logits_processor = LogitsProcessorList()
+        logits_processor.append(InvalidScoreLogitsProcessor())
+        gen_kwargs = {"max_length": max_length, "do_sample": do_sample, "top_p": top_p,
+                      "temperature": temperature, "logits_processor": logits_processor, **kwargs}
+        inputs = self.build_inputs(tokenizer, query, history=history)
+        for outputs in self.stream_generate(**inputs, **gen_kwargs):
+            outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):]
+            response = tokenizer.decode(outputs)
+            response = self.process_response(response)
+            new_history = history + [(query, response)]
+            yield response, new_history
+
+    @torch.no_grad()
+    def stream_generate(
+            self,
+            input_ids,
+            generation_config: Optional[GenerationConfig] = None,
+            logits_processor: Optional[LogitsProcessorList] = None,
+            stopping_criteria: Optional[StoppingCriteriaList] = None,
+            prefix_allowed_tokens_fn: Optional[Callable[[int, torch.Tensor], List[int]]] = None,
+            **kwargs,
+    ):
+        batch_size, input_ids_seq_length = input_ids.shape[0], input_ids.shape[-1]
+
+        if generation_config is None:
+            generation_config = self.generation_config
+        generation_config = copy.deepcopy(generation_config)
+        model_kwargs = generation_config.update(**kwargs)
+        bos_token_id, eos_token_id = generation_config.bos_token_id, generation_config.eos_token_id
+
+        if isinstance(eos_token_id, int):
+            eos_token_id = [eos_token_id]
+
+        has_default_max_length = kwargs.get("max_length") is None and generation_config.max_length is not None
+        if has_default_max_length and generation_config.max_new_tokens is None:
+            warnings.warn(
+                f"Using `max_length`'s default ({generation_config.max_length}) to control the generation length. "
+                "This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we"
+                " recommend using `max_new_tokens` to control the maximum length of the generation.",
+                UserWarning,
+            )
+        elif generation_config.max_new_tokens is not None:
+            generation_config.max_length = generation_config.max_new_tokens + input_ids_seq_length
+            if not has_default_max_length:
+                logger.warn(
+                    f"Both `max_new_tokens` (={generation_config.max_new_tokens}) and `max_length`(="
+                    f"{generation_config.max_length}) seem to have been set. `max_new_tokens` will take precedence. "
+                    "Please refer to the documentation for more information. "
+                    "(https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)",
+                    UserWarning,
+                )
+
+        if input_ids_seq_length >= generation_config.max_length:
+            input_ids_string = "decoder_input_ids" if self.config.is_encoder_decoder else "input_ids"
+            logger.warning(
+                f"Input length of {input_ids_string} is {input_ids_seq_length}, but `max_length` is set to"
+                f" {generation_config.max_length}. This can lead to unexpected behavior. You should consider"
+                " increasing `max_new_tokens`."
+            )
+
+        # 2. Set generation parameters if not already defined
+        logits_processor = logits_processor if logits_processor is not None else LogitsProcessorList()
+        stopping_criteria = stopping_criteria if stopping_criteria is not None else StoppingCriteriaList()
+
+        logits_processor = self._get_logits_processor(
+            generation_config=generation_config,
+            input_ids_seq_length=input_ids_seq_length,
+            encoder_input_ids=input_ids,
+            prefix_allowed_tokens_fn=prefix_allowed_tokens_fn,
+            logits_processor=logits_processor,
+        )
+
+        stopping_criteria = self._get_stopping_criteria(
+            generation_config=generation_config, stopping_criteria=stopping_criteria
+        )
+        logits_warper = self._get_logits_warper(generation_config)
+
+        unfinished_sequences = input_ids.new(input_ids.shape[0]).fill_(1)
+        scores = None
+        while True:
+            model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)
+            # forward pass to get next token
+            outputs = self(
+                **model_inputs,
+                return_dict=True,
+                output_attentions=False,
+                output_hidden_states=False,
+            )
+
+            next_token_logits = outputs.logits[:, -1, :]
+
+            # pre-process distribution
+            next_token_scores = logits_processor(input_ids, next_token_logits)
+            next_token_scores = logits_warper(input_ids, next_token_scores)
+
+            # sample
+            probs = nn.functional.softmax(next_token_scores, dim=-1)
+            if generation_config.do_sample:
+                next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1)
+            else:
+                next_tokens = torch.argmax(probs, dim=-1)
+
+            # update generated ids, model inputs, and length for next step
+            input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1)
+            model_kwargs = self._update_model_kwargs_for_generation(
+                outputs, model_kwargs, is_encoder_decoder=self.config.is_encoder_decoder
+            )
+            unfinished_sequences = unfinished_sequences.mul((sum(next_tokens != i for i in eos_token_id)).long())
+
+            # stop when each sentence is finished, or if we exceed the maximum length
+            if unfinished_sequences.max() == 0 or stopping_criteria(input_ids, scores):
+                break
+            yield input_ids
+
+    def quantize(self, bits: int, empty_init=False, device=None, **kwargs):
+        if bits == 0:
+            return
+
+        from .quantization import quantize
+
+        if self.quantized:
+            logger.info("Already quantized.")
+            return self
+
+        self.quantized = True
+
+        self.config.quantization_bit = bits
+
+        self.transformer.encoder = quantize(self.transformer.encoder, bits, empty_init=empty_init, device=device,
+                                            **kwargs)
+        return self

pytorch_model-00001-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d9ea931a3cb444ad53fd33853e003d22953a5fcd34204e6df7fb61d746b748
+size 1827781090

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7706f7420577fbe254f2f80c430084cec9c6879de5094a94a627f9d2517a5c8d
+size 1968299480

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb6903f7cc06c3bd1be76a2880a56f92ae9e8c6a734380d9ce48d98f5bba958
+size 1927415036

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3412c7584797d1576dc8ff55ad0d863f6c3b52d1da720a2d3a45266ebed568
+size 1815225998

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdfddc4596fc323ea16be00059d0e7cf255e180c1818c92138137f3c260b4c06
+size 1968299544

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19d2d2f1bccbca9a7f09fcd8975191e435acd5be0a557a51140dc6d8a1fffa5
+size 1927415036

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bde960e5c66595c46022163579938d0e0c3e37f6b006b2d1249ba85407b5e1c
+size 1052808542

pytorch_model.bin.index.json

@@ -0,0 +1,207 @@
+{
+  "metadata": {
+    "total_size": 12487168064
+  },
+  "weight_map": {
+    "transformer.embedding.word_embeddings.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.final_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.encoder.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.1.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.10.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.11.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.12.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.13.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.14.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.15.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.16.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.17.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.encoder.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.18.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.19.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.2.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.20.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.21.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.22.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.23.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.24.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.25.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.26.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.encoder.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.encoder.layers.27.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.encoder.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.3.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.encoder.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.4.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.5.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.6.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.7.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.8.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.9.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.output_layer.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.rotary_pos_emb.inv_freq": "pytorch_model-00001-of-00007.bin"
+  }
+}

quantization.py

@@ -0,0 +1,190 @@
+from torch.nn import Linear
+from torch.nn.parameter import Parameter
+
+import bz2
+import torch
+import base64
+import ctypes
+from transformers.utils import logging
+
+from typing import List
+from functools import partial
+
+logger = logging.get_logger(__name__)
+
+try:
+    from cpm_kernels.kernels.base import LazyKernelCModule, KernelFunction, round_up
+
+    class Kernel:
+        def __init__(self, code: bytes, function_names: List[str]):
+            self.code = code
+            self._function_names = function_names
+            self._cmodule = LazyKernelCModule(self.code)
+
+            for name in self._function_names:
+                setattr(self, name, KernelFunction(self._cmodule, name))
+
+    quantization_code = "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"
+
+    kernels = Kernel(
+        bz2.decompress(base64.b64decode(quantization_code)),
+        [
+            "int4WeightCompression",
+            "int4WeightExtractionFloat",
+            "int4WeightExtractionHalf",
+            "int4WeightExtractionBFloat16",
+            "int8WeightExtractionFloat",
+            "int8WeightExtractionHalf",
+            "int8WeightExtractionBFloat16",
+        ],
+    )
+except Exception as exception:
+    kernels = None
+    logger.warning("Failed to load cpm_kernels:" + str(exception))
+
+
+class W8A16Linear(torch.autograd.Function):
+    @staticmethod
+    def forward(ctx, inp: torch.Tensor, quant_w: torch.Tensor, scale_w: torch.Tensor, weight_bit_width):
+        ctx.inp_shape = inp.size()
+        ctx.weight_bit_width = weight_bit_width
+        out_features = quant_w.size(0)
+        inp = inp.contiguous().view(-1, inp.size(-1))
+        weight = extract_weight_to_half(quant_w, scale_w, weight_bit_width)
+        ctx.weight_shape = weight.size()
+        output = inp.mm(weight.t())
+        ctx.save_for_backward(inp, quant_w, scale_w)
+        return output.view(*(ctx.inp_shape[:-1] + (out_features,)))
+
+    @staticmethod
+    def backward(ctx, grad_output: torch.Tensor):
+        inp, quant_w, scale_w = ctx.saved_tensors
+        weight = extract_weight_to_half(quant_w, scale_w, ctx.weight_bit_width)
+        grad_output = grad_output.contiguous().view(-1, weight.size(0))
+        grad_input = grad_output.mm(weight)
+        grad_weight = grad_output.t().mm(inp)
+        return grad_input.view(ctx.inp_shape), grad_weight.view(ctx.weight_shape), None, None
+
+
+def compress_int4_weight(weight: torch.Tensor):  # (n, m)
+    with torch.cuda.device(weight.device):
+        n, m = weight.size(0), weight.size(1)
+        assert m % 2 == 0
+        m = m // 2
+        out = torch.empty(n, m, dtype=torch.int8, device="cuda")
+        stream = torch.cuda.current_stream()
+
+        gridDim = (n, 1, 1)
+        blockDim = (min(round_up(m, 32), 1024), 1, 1)
+
+        kernels.int4WeightCompression(
+            gridDim,
+            blockDim,
+            0,
+            stream,
+            [ctypes.c_void_p(weight.data_ptr()), ctypes.c_void_p(out.data_ptr()), ctypes.c_int32(n), ctypes.c_int32(m)],
+        )
+        return out
+
+
+def extract_weight_to_half(weight: torch.Tensor, scale_list: torch.Tensor, source_bit_width: int):
+    assert scale_list.dtype in [torch.half, torch.bfloat16]
+    assert weight.dtype in [torch.int8]
+    if source_bit_width == 8:
+        return weight.to(scale_list.dtype) * scale_list[:, None]
+    elif source_bit_width == 4:
+        func = (
+            kernels.int4WeightExtractionHalf if scale_list.dtype == torch.half else kernels.int4WeightExtractionBFloat16
+        )
+    else:
+        assert False, "Unsupported bit-width"
+
+    with torch.cuda.device(weight.device):
+        n, m = weight.size(0), weight.size(1)
+        out = torch.empty(n, m * (8 // source_bit_width), dtype=scale_list.dtype, device="cuda")
+        stream = torch.cuda.current_stream()
+
+        gridDim = (n, 1, 1)
+        blockDim = (min(round_up(m, 32), 1024), 1, 1)
+
+        func(
+            gridDim,
+            blockDim,
+            0,
+            stream,
+            [
+                ctypes.c_void_p(weight.data_ptr()),
+                ctypes.c_void_p(scale_list.data_ptr()),
+                ctypes.c_void_p(out.data_ptr()),
+                ctypes.c_int32(n),
+                ctypes.c_int32(m),
+            ],
+        )
+        return out
+
+
+class QuantizedLinear(torch.nn.Module):
+    def __init__(self, weight_bit_width: int, weight, bias=None, device="cpu", dtype=None, empty_init=False, *args,
+                 **kwargs):
+        super().__init__()
+        self.weight_bit_width = weight_bit_width
+
+        shape = weight.shape
+
+        if weight is None or empty_init:
+            self.weight = torch.empty(shape[0], shape[1] * weight_bit_width // 8, dtype=torch.int8, device=device)
+            self.weight_scale = torch.empty(shape[0], dtype=dtype, device=device)
+        else:
+            self.weight_scale = weight.abs().max(dim=-1).values / ((2 ** (weight_bit_width - 1)) - 1)
+            self.weight = torch.round(weight / self.weight_scale[:, None]).to(torch.int8)
+            if weight_bit_width == 4:
+                self.weight = compress_int4_weight(self.weight)
+
+        self.weight = Parameter(self.weight.to(device), requires_grad=False)
+        self.weight_scale = Parameter(self.weight_scale.to(device), requires_grad=False)
+        self.bias = Parameter(bias.to(device), requires_grad=False) if bias is not None else None
+
+    def forward(self, input):
+        output = W8A16Linear.apply(input, self.weight, self.weight_scale, self.weight_bit_width)
+        if self.bias is not None:
+            output = output + self.bias
+        return output
+
+
+def quantize(model, weight_bit_width, empty_init=False, device=None):
+    """Replace fp16 linear with quantized linear"""
+    for layer in model.layers:
+        layer.self_attention.query_key_value = QuantizedLinear(
+            weight_bit_width=weight_bit_width,
+            weight=layer.self_attention.query_key_value.weight.to(torch.cuda.current_device()),
+            bias=layer.self_attention.query_key_value.bias,
+            dtype=layer.self_attention.query_key_value.weight.dtype,
+            device=layer.self_attention.query_key_value.weight.device if device is None else device,
+            empty_init=empty_init
+        )
+        layer.self_attention.dense = QuantizedLinear(
+            weight_bit_width=weight_bit_width,
+            weight=layer.self_attention.dense.weight.to(torch.cuda.current_device()),
+            bias=layer.self_attention.dense.bias,
+            dtype=layer.self_attention.dense.weight.dtype,
+            device=layer.self_attention.dense.weight.device if device is None else device,
+            empty_init=empty_init
+        )
+        layer.mlp.dense_h_to_4h = QuantizedLinear(
+            weight_bit_width=weight_bit_width,
+            weight=layer.mlp.dense_h_to_4h.weight.to(torch.cuda.current_device()),
+            bias=layer.mlp.dense_h_to_4h.bias,
+            dtype=layer.mlp.dense_h_to_4h.weight.dtype,
+            device=layer.mlp.dense_h_to_4h.weight.device if device is None else device,
+            empty_init=empty_init
+        )
+        layer.mlp.dense_4h_to_h = QuantizedLinear(
+            weight_bit_width=weight_bit_width,
+            weight=layer.mlp.dense_4h_to_h.weight.to(torch.cuda.current_device()),
+            bias=layer.mlp.dense_4h_to_h.bias,
+            dtype=layer.mlp.dense_4h_to_h.weight.dtype,
+            device=layer.mlp.dense_4h_to_h.weight.device if device is None else device,
+            empty_init=empty_init
+        )
+
+    return model

tokenization_chatglm.py

@@ -0,0 +1,236 @@
+import os
+import torch
+from typing import List, Optional, Union, Dict
+from sentencepiece import SentencePieceProcessor
+from transformers import PreTrainedTokenizer
+from transformers.utils import logging, PaddingStrategy
+from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
+
+
+class SPTokenizer:
+    def __init__(self, model_path: str):
+        # reload tokenizer
+        assert os.path.isfile(model_path), model_path
+        self.sp_model = SentencePieceProcessor(model_file=model_path)
+
+        # BOS / EOS token IDs
+        self.n_words: int = self.sp_model.vocab_size()
+        self.bos_id: int = self.sp_model.bos_id()
+        self.eos_id: int = self.sp_model.eos_id()
+        self.pad_id: int = self.sp_model.eos_id()
+        assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()
+
+        special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "sop", "eop"]
+        self.special_tokens = {}
+        self.index_special_tokens = {}
+        for token in special_tokens:
+            self.special_tokens[token] = self.n_words
+            self.index_special_tokens[self.n_words] = token
+            self.n_words += 1
+
+    def tokenize(self, s: str):
+        return self.sp_model.EncodeAsPieces(s)
+
+    def encode(self, s: str, bos: bool = False, eos: bool = False) -> List[int]:
+        assert type(s) is str
+        t = self.sp_model.encode(s)
+        if bos:
+            t = [self.bos_id] + t
+        if eos:
+            t = t + [self.eos_id]
+        return t
+
+    def decode(self, t: List[int]) -> str:
+        return self.sp_model.decode(t)
+
+    def decode_tokens(self, tokens: List[str]) -> str:
+        text = self.sp_model.DecodePieces(tokens)
+        return text
+
+    def convert_token_to_id(self, token):
+        """ Converts a token (str) in an id using the vocab. """
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        return self.sp_model.PieceToId(token)
+
+    def convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        if index in self.index_special_tokens:
+            return ""
+        return self.sp_model.IdToPiece(index)
+
+
+class ChatGLMTokenizer(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", **kwargs):
+        super().__init__(padding_side=padding_side, clean_up_tokenization_spaces=False, **kwargs)
+        self.name = "GLMTokenizer"
+
+        self.tokenizer = SPTokenizer(vocab_file)
+        self.special_tokens = {
+            "<bos>": self.tokenizer.bos_id,
+            "<eos>": self.tokenizer.eos_id,
+            "<pad>": self.tokenizer.pad_id
+        }
+
+    def get_command(self, token):
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        assert token in self.tokenizer.special_tokens, f"{token} is not a special token for {self.name}"
+        return self.tokenizer.special_tokens[token]
+
+    @property
+    def pad_token(self) -> str:
+        return "</s>"
+
+    @property
+    def pad_token_id(self):
+        return self.get_command("<pad>")
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.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 _tokenize(self, text, **kwargs):
+        return self.tokenizer.tokenize(text)
+
+    def _convert_token_to_id(self, token):
+        """ Converts a token (str) in an id using the vocab. """
+        return self.tokenizer.convert_token_to_id(token)
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.tokenizer.convert_id_to_token(index)
+
+    def convert_tokens_to_string(self, tokens: List[str]) -> str:
+        return self.tokenizer.decode_tokens(tokens)
+
+    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.get_command("[gMASK]"), self.get_command("sop")]
+        return prefix_tokens
+
+    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.get_command("<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,
+            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 max_length is not None:
+            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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d9fdbdfaa7cd8c0a3a38d7e8de2e6c31374b5dbc4dc4568d85585fe745812f
+size 1018370

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "name_or_path": "THUDM/codegeex2-6b",
+  "remove_space": false,
+  "do_lower_case": false,
+  "tokenizer_class": "ChatGLMTokenizer",
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_chatglm.ChatGLMTokenizer",
+      null
+      ]
+  }
+}