generated from xuyuqing/ailab
add model
This commit is contained in:
aicloud
parent
d8d35d822d
commit
42494d7d66
|
|
@ -0,0 +1 @@
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
@ -0,0 +1,33 @@
|
||||||
|
The ChatGLM2-6B License
|
||||||
|
|
||||||
|
1. Definitions
|
||||||
|
|
||||||
|
“Licensor” means the ChatGLM2-6B Model Team that distributes its Software.
|
||||||
|
|
||||||
|
“Software” means the ChatGLM2-6B 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 solely for your non-commercial research purposes.
|
||||||
|
|
||||||
|
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 commercial, 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 glm-130b@googlegroups.com.
|
||||||
95
README.md
95
README.md
|
|
@ -0,0 +1,95 @@
|
||||||
|
---
|
||||||
|
language:
|
||||||
|
- zh
|
||||||
|
- en
|
||||||
|
tags:
|
||||||
|
- glm
|
||||||
|
- chatglm
|
||||||
|
- thudm
|
||||||
|
---
|
||||||
|
# ChatGLM2-6B
|
||||||
|
<p align="center">
|
||||||
|
💻 <a href="https://github.com/THUDM/ChatGLM2-6B" target="_blank">Github Repo</a> • 🐦 <a href="https://twitter.com/thukeg" target="_blank">Twitter</a> • 📃 <a href="https://arxiv.org/abs/2103.10360" target="_blank">[GLM@ACL 22]</a> <a href="https://github.com/THUDM/GLM" target="_blank">[GitHub]</a> • 📃 <a href="https://arxiv.org/abs/2210.02414" target="_blank">[GLM-130B@ICLR 23]</a> <a href="https://github.com/THUDM/GLM-130B" target="_blank">[GitHub]</a> <br>
|
||||||
|
</p>
|
||||||
|
|
||||||
|
<p align="center">
|
||||||
|
👋 Join our <a href="https://join.slack.com/t/chatglm/shared_invite/zt-1y7pqoloy-9b1g6T6JjA8J0KxvUjbwJw" target="_blank">Slack</a> and <a href="https://github.com/THUDM/ChatGLM-6B/blob/main/resources/WECHAT.md" target="_blank">WeChat</a>
|
||||||
|
</p>
|
||||||
|
|
||||||
|
## 介绍
|
||||||
|
ChatGLM**2**-6B 是开源中英双语对话模型 [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B) 的第二代版本，在保留了初代模型对话流畅、部署门槛较低等众多优秀特性的基础之上，ChatGLM**2**-6B 引入了如下新特性：
|
||||||
|
|
||||||
|
1. **更强大的性能**：基于 ChatGLM 初代模型的开发经验，我们全面升级了 ChatGLM2-6B 的基座模型。ChatGLM2-6B 使用了 [GLM](https://github.com/THUDM/GLM) 的混合目标函数，经过了 1.4T 中英标识符的预训练与人类偏好对齐训练，[评测结果](#评测结果)显示，相比于初代模型，ChatGLM2-6B 在 MMLU（+23%）、CEval（+33%）、GSM8K（+571%） 、BBH（+60%）等数据集上的性能取得了大幅度的提升，在同尺寸开源模型中具有较强的竞争力。
|
||||||
|
2. **更长的上下文**：基于 [FlashAttention](https://github.com/HazyResearch/flash-attention) 技术，我们将基座模型的上下文长度（Context Length）由 ChatGLM-6B 的 2K 扩展到了 32K，并在对话阶段使用 8K 的上下文长度训练，允许更多轮次的对话。但当前版本的 ChatGLM2-6B 对单轮超长文档的理解能力有限，我们会在后续迭代升级中着重进行优化。
|
||||||
|
3. **更高效的推理**：基于 [Multi-Query Attention](http://arxiv.org/abs/1911.02150) 技术，ChatGLM2-6B 有更高效的推理速度和更低的显存占用：在官方的模型实现下，推理速度相比初代提升了 42%，INT4 量化下，6G 显存支持的对话长度由 1K 提升到了 8K。
|
||||||
|
|
||||||
|
ChatGLM**2**-6B is the second-generation version of the open-source bilingual (Chinese-English) chat model [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B). It retains the smooth conversation flow and low deployment threshold of the first-generation model, while introducing the following new features:
|
||||||
|
|
||||||
|
1. **Stronger Performance**: Based on the development experience of the first-generation ChatGLM model, we have fully upgraded the base model of ChatGLM2-6B. ChatGLM2-6B uses the hybrid objective function of [GLM](https://github.com/THUDM/GLM), and has undergone pre-training with 1.4T bilingual tokens and human preference alignment training. The [evaluation results](README.md#evaluation-results) show that, compared to the first-generation model, ChatGLM2-6B has achieved substantial improvements in performance on datasets like MMLU (+23%), CEval (+33%), GSM8K (+571%), BBH (+60%), showing strong competitiveness among models of the same size.
|
||||||
|
2. **Longer Context**: Based on [FlashAttention](https://github.com/HazyResearch/flash-attention) technique, we have extended the context length of the base model from 2K in ChatGLM-6B to 32K, and trained with a context length of 8K during the dialogue alignment, allowing for more rounds of dialogue. However, the current version of ChatGLM2-6B has limited understanding of single-round ultra-long documents, which we will focus on optimizing in future iterations.
|
||||||
|
3. **More Efficient Inference**: Based on [Multi-Query Attention](http://arxiv.org/abs/1911.02150) technique, ChatGLM2-6B has more efficient inference speed and lower GPU memory usage: under the official implementation, the inference speed has increased by 42% compared to the first generation; under INT4 quantization, the dialogue length supported by 6G GPU memory has increased from 1K to 8K.
|
||||||
|
|
||||||
|
## 软件依赖
|
||||||
|
|
||||||
|
```shell
|
||||||
|
pip install protobuf transformers==4.30.2 cpm_kernels torch>=2.0 gradio mdtex2html sentencepiece accelerate
|
||||||
|
```
|
||||||
|
|
||||||
|
## 代码调用
|
||||||
|
|
||||||
|
可以通过如下代码调用 ChatGLM-6B 模型来生成对话：
|
||||||
|
|
||||||
|
```ipython
|
||||||
|
>>> from transformers import AutoTokenizer, AutoModel
|
||||||
|
>>> tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
|
||||||
|
>>> model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
|
||||||
|
>>> model = model.eval()
|
||||||
|
>>> response, history = model.chat(tokenizer, "你好", history=[])
|
||||||
|
>>> print(response)
|
||||||
|
你好👋!我是人工智能助手 ChatGLM-6B,很高兴见到你,欢迎问我任何问题。
|
||||||
|
>>> response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history)
|
||||||
|
>>> print(response)
|
||||||
|
晚上睡不着可能会让你感到焦虑或不舒服,但以下是一些可以帮助你入睡的方法:
|
||||||
|
|
||||||
|
1. 制定规律的睡眠时间表:保持规律的睡眠时间表可以帮助你建立健康的睡眠习惯,使你更容易入睡。尽量在每天的相同时间上床,并在同一时间起床。
|
||||||
|
2. 创造一个舒适的睡眠环境:确保睡眠环境舒适,安静,黑暗且温度适宜。可以使用舒适的床上用品,并保持房间通风。
|
||||||
|
3. 放松身心:在睡前做些放松的活动,例如泡个热水澡,听些轻柔的音乐,阅读一些有趣的书籍等,有助于缓解紧张和焦虑,使你更容易入睡。
|
||||||
|
4. 避免饮用含有咖啡因的饮料:咖啡因是一种刺激性物质,会影响你的睡眠质量。尽量避免在睡前饮用含有咖啡因的饮料,例如咖啡,茶和可乐。
|
||||||
|
5. 避免在床上做与睡眠无关的事情:在床上做些与睡眠无关的事情,例如看电影,玩游戏或工作等,可能会干扰你的睡眠。
|
||||||
|
6. 尝试呼吸技巧:深呼吸是一种放松技巧,可以帮助你缓解紧张和焦虑,使你更容易入睡。试着慢慢吸气,保持几秒钟,然后缓慢呼气。
|
||||||
|
|
||||||
|
如果这些方法无法帮助你入睡,你可以考虑咨询医生或睡眠专家,寻求进一步的建议。
|
||||||
|
```
|
||||||
|
|
||||||
|
关于更多的使用说明，包括如何运行命令行和网页版本的 DEMO，以及使用模型量化以节省显存，请参考我们的 [Github Repo](https://github.com/THUDM/ChatGLM2-6B)。
|
||||||
|
|
||||||
|
For more instructions, including how to run CLI and web demos, and model quantization, please refer to our [Github Repo](https://github.com/THUDM/ChatGLM2-6B).
|
||||||
|
|
||||||
|
## Change Log
|
||||||
|
* v1.0
|
||||||
|
|
||||||
|
## 协议
|
||||||
|
|
||||||
|
本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源，ChatGLM2-6B 模型的权重的使用则需要遵循 [Model License](MODEL_LICENSE)。
|
||||||
|
|
||||||
|
## 引用
|
||||||
|
|
||||||
|
如果你觉得我们的工作有帮助的话，请考虑引用下列论文，ChatGLM2-6B 的论文会在近期公布，尽情期待～
|
||||||
|
|
||||||
|
```
|
||||||
|
@article{zeng2022glm,
|
||||||
|
title={Glm-130b: An open bilingual pre-trained model},
|
||||||
|
author={Zeng, Aohan and Liu, Xiao and Du, Zhengxiao and Wang, Zihan and Lai, Hanyu and Ding, Ming and Yang, Zhuoyi and Xu, Yifan and Zheng, Wendi and Xia, Xiao and others},
|
||||||
|
journal={arXiv preprint arXiv:2210.02414},
|
||||||
|
year={2022}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
```
|
||||||
|
@inproceedings{du2022glm,
|
||||||
|
title={GLM: General Language Model Pretraining with Autoregressive Blank Infilling},
|
||||||
|
author={Du, Zhengxiao and Qian, Yujie and Liu, Xiao and Ding, Ming and Qiu, Jiezhong and Yang, Zhilin and Tang, Jie},
|
||||||
|
booktitle={Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
|
||||||
|
pages={320--335},
|
||||||
|
year={2022}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
@ -0,0 +1,40 @@
|
||||||
|
{
|
||||||
|
"_name_or_path": "THUDM/chatglm2-6b",
|
||||||
|
"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,
|
||||||
|
"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,
|
||||||
|
"seq_length": 32768,
|
||||||
|
"use_cache": true,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.27.1",
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"pad_token_id": 0
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,60 @@
|
||||||
|
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,
|
||||||
|
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,
|
||||||
|
pre_seq_len=None,
|
||||||
|
prefix_projection=False,
|
||||||
|
**kwargs
|
||||||
|
):
|
||||||
|
self.num_layers = num_layers
|
||||||
|
self.vocab_size = padded_vocab_size
|
||||||
|
self.padded_vocab_size = padded_vocab_size
|
||||||
|
self.hidden_size = hidden_size
|
||||||
|
self.ffn_hidden_size = ffn_hidden_size
|
||||||
|
self.kv_channels = kv_channels
|
||||||
|
self.num_attention_heads = num_attention_heads
|
||||||
|
self.seq_length = seq_length
|
||||||
|
self.hidden_dropout = hidden_dropout
|
||||||
|
self.attention_dropout = attention_dropout
|
||||||
|
self.layernorm_epsilon = layernorm_epsilon
|
||||||
|
self.rmsnorm = rmsnorm
|
||||||
|
self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
|
||||||
|
self.post_layer_norm = post_layer_norm
|
||||||
|
self.add_bias_linear = add_bias_linear
|
||||||
|
self.add_qkv_bias = add_qkv_bias
|
||||||
|
self.bias_dropout_fusion = bias_dropout_fusion
|
||||||
|
self.multi_query_attention = multi_query_attention
|
||||||
|
self.multi_query_group_num = multi_query_group_num
|
||||||
|
self.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
|
||||||
|
self.pre_seq_len = pre_seq_len
|
||||||
|
self.prefix_projection = prefix_projection
|
||||||
|
super().__init__(**kwargs)
|
||||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -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"
|
||||||
|
}
|
||||||
|
}
|
||||||
File diff suppressed because one or more lines are too long
|
|
@ -0,0 +1,253 @@
|
||||||
|
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.unk_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 or index in [self.eos_id, self.bos_id, self.pad_id] or index < 0:
|
||||||
|
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, **kwargs)
|
||||||
|
self.name = "GLMTokenizer"
|
||||||
|
|
||||||
|
self.vocab_file = vocab_file
|
||||||
|
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 "<unk>"
|
||||||
|
|
||||||
|
@property
|
||||||
|
def pad_token_id(self):
|
||||||
|
return self.get_command("<pad>")
|
||||||
|
|
||||||
|
@property
|
||||||
|
def eos_token(self) -> str:
|
||||||
|
return "</s>"
|
||||||
|
|
||||||
|
@property
|
||||||
|
def eos_token_id(self):
|
||||||
|
return self.get_command("<eos>")
|
||||||
|
|
||||||
|
@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_prompt(self, query, history=None):
|
||||||
|
if history is None:
|
||||||
|
history = []
|
||||||
|
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)
|
||||||
|
return prompt
|
||||||
|
|
||||||
|
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 "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
|
||||||
Binary file not shown.
|
|
@ -0,0 +1,12 @@
|
||||||
|
{
|
||||||
|
"name_or_path": "THUDM/chatglm2-6b",
|
||||||
|
"remove_space": false,
|
||||||
|
"do_lower_case": false,
|
||||||
|
"tokenizer_class": "ChatGLMTokenizer",
|
||||||
|
"auto_map": {
|
||||||
|
"AutoTokenizer": [
|
||||||
|
"tokenization_chatglm.ChatGLMTokenizer",
|
||||||
|
null
|
||||||
|
]
|
||||||
|
}
|
||||||
|
}
|
||||||
Loading…
Reference in New Issue