update readme

Former-commit-id: 561481a8008fde5a3273558460193864a09866ed
set version
2023-11-21 13:15:46 +08:00 · 2023-11-20 22:57:44 +08:00 · 2023-11-20 22:52:11 +08:00 · 2023-11-20 21:39:15 +08:00 · 2023-11-20 20:32:55 +08:00 · 2023-11-20 19:01:37 +08:00
29 changed files with 1597 additions and 186 deletions
--- a/.github/ISSUE_TEMPLATE/bug-report.yml
+++ b/.github/ISSUE_TEMPLATE/bug-report.yml
@@ -0,0 +1,58 @@
+name: "\U0001F41B Bug / Help"
+description: Create a report to help us improve the LLaMA Factory
+body:
+  - type: checkboxes
+    id: reminder
+    attributes:
+      label: Reminder
+      description: |
+        Please ensure you have read the README carefully and searched the existing issues.
+        请确保您已经认真阅读了 README 并且搜索过现有的 Issue。
+
+      options:
+        - label: I have read the README and searched the existing issues.
+          required: true
+
+  - type: textarea
+    id: reproduction
+    validations:
+      required: true
+    attributes:
+      label: Reproduction
+      description: |
+        Please provide code snippets, error messages and stack traces that reproduces the problem.
+        请提供运行参数，错误信息以及异常堆栈以便于我们复现该问题。
+        Remember to use Markdown tags to correctly format your code.
+        请合理使用 Markdown 标签来格式化您的文本。
+
+      placeholder: |
+        python src/train_bash.py ...
+
+  - type: textarea
+    id: expected-behavior
+    validations:
+      required: false
+    attributes:
+      label: Expected behavior
+      description: |
+        Please provide a clear and concise description of what you would expect to happen.
+        请提供您原本的目的，即这段代码的期望行为。
+
+  - type: textarea
+    id: system-info
+    validations:
+      required: false
+    attributes:
+      label: System Info
+      description: |
+        Please share your system info with us. You can run the command **transformers-cli env** and copy-paste its output below.
+        请提供您的系统信息。您可以在命令行运行 **transformers-cli env** 并将其输出复制到该文本框中。
+
+      placeholder: transformers version, platform, python version, ...
+
+  - type: textarea
+    id: others
+    validations:
+      required: false
+    attributes:
+      label: Others
--- a/README.md
+++ b/README.md
@@ -8,6 +8,7 @@
 [![GitHub pull request](https://img.shields.io/badge/PRs-welcome-blue)](https://github.com/hiyouga/LLaMA-Factory/pulls)
 [![Discord](https://dcbadge.vercel.app/api/server/c2EPEt5NU?compact=true&style=flat)](https://discord.gg/c2EPEt5NU)
 [![Spaces](https://img.shields.io/badge/🤗-Open%20In%20Spaces-blue)](https://huggingface.co/spaces/hiyouga/LLaMA-Board)
+[![Studios](https://img.shields.io/badge/ModelScope-Open%20In%20Studios-blue)](https://modelscope.cn/studios/hiyouga/LLaMA-Board)

 👋 Join our [WeChat](assets/wechat.jpg).

@@ -15,14 +16,39 @@

 ## LLaMA Board: A One-stop Web UI for Getting Started with LLaMA Factory

-Preview LLaMA Board at **[🤗 Spaces](https://huggingface.co/spaces/hiyouga/LLaMA-Board)**.
+Preview LLaMA Board at **[🤗 Spaces](https://huggingface.co/spaces/hiyouga/LLaMA-Board)** or **[ModelScope](https://modelscope.cn/studios/hiyouga/LLaMA-Board)**.

-Launch LLaMA Board via `CUDA_VISIBLE_DEVICES=0 python src/train_web.py`. (multiple GPUs are not supported yet)
+Launch LLaMA Board via `CUDA_VISIBLE_DEVICES=0 python src/train_web.py`. (multiple GPUs are not supported yet in this mode)

 Here is an example of altering the self-cognition of an instruction-tuned language model within 10 minutes on a single GPU.

 https://github.com/hiyouga/LLaMA-Factory/assets/16256802/6ba60acc-e2e2-4bec-b846-2d88920d5ba1

+## Table of Contents
+
+- [Benchmark](#benchmark)
+- [Changelog](#changelog)
+- [Supported Models](#supported-models)
+- [Supported Training Approaches](#supported-training-approaches)
+- [Provided Datasets](#provided-datasets)
+- [Requirement](#requirement)
+- [Getting Started](#getting-started)
+- [Projects using LLaMA Factory](#projects-using-llama-factory)
+- [License](#license)
+- [Citation](#citation)
+- [Acknowledgement](#acknowledgement)
+
+## Benchmark
+
+Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ptuning), LLaMA-Factory's LoRA tuning offers up to **3.7 times faster** training speed with a better Rouge score on the advertising text generation task. By leveraging 4-bit quantization technique, LLaMA-Factory's QLoRA further improves the efficiency regarding the GPU memory.
+
+![benchmark](assets/benchmark.svg)
+
+- **Training Speed**: the number of training samples processed per second during the training. (bs=4, cutoff_len=1024)
+- **Rouge Score**: Rouge-2 score on the development set of the [advertising text generation](https://aclanthology.org/D19-1321.pdf) task. (bs=4, cutoff_len=1024)
+- **GPU Memory**: Peak GPU memory usage in 4-bit quantized training. (bs=1, cutoff_len=1024)
+- We adopt `pre_seq_len=128` for ChatGLM's P-Tuning and `lora_rank=32` for LLaMA-Factory's LoRA tuning.
+
 ## Changelog

 [23/10/21] We supported **[NEFTune](https://arxiv.org/abs/2310.05914)** trick for fine-tuning. Try `--neft_alpha` argument to activate NEFTune, e.g., `--neft_alpha 5`.
@@ -288,6 +314,8 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
    --per_device_train_batch_size 2 \
    --gradient_accumulation_steps 4 \
    --lr_scheduler_type cosine \
+    --top_k 0 \
+    --top_p 0.9 \
    --logging_steps 10 \
    --save_steps 1000 \
    --learning_rate 1e-5 \
@@ -296,6 +324,9 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
    --fp16
 ```

+> [!WARNING]
+> Use `--per_device_train_batch_size=1` for LLaMA-2 models in fp16 PPO training.
+
 #### DPO Training

 ```bash
@@ -391,7 +422,7 @@ deepspeed --num_gpus 8 --master_port=9901 src/train_bash.py \

 </details>

-### Export model
+### Merge LoRA weights and export model

 ```bash
 python src/export_model.py \
@@ -412,7 +443,7 @@ python src/api_demo.py \
    --checkpoint_dir path_to_checkpoint
 ```

-> [!NOTE]
+> [!TIP]
 > Visit `http://localhost:8000/docs` for API documentation.

 ### CLI Demo
@@ -464,10 +495,14 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
    --output_dir path_to_predict_result \
    --per_device_eval_batch_size 8 \
    --max_samples 100 \
-    --predict_with_generate
+    --predict_with_generate \
+    --fp16
 ```

-> [!NOTE]
+> [!WARNING]
+> Use `--per_device_train_batch_size=1` for LLaMA-2 models in fp16 predict.
+
+> [!TIP]
 > We recommend using `--per_device_eval_batch_size=1` and `--max_target_length 128` at 4/8-bit predict.

 ## Projects using LLaMA Factory
@@ -477,6 +512,9 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
 - **[Sunsimiao](https://github.com/thomas-yanxin/Sunsimiao)**: A large language model specialized in Chinese medical domain, based on Baichuan-7B and ChatGLM-6B.
 - **[CareGPT](https://github.com/WangRongsheng/CareGPT)**: A series of large language models for Chinese medical domain, based on LLaMA2-7B and Baichuan-13B.

+> [!TIP]
+> If you have a project that should be incorporated, please contact via email or create a pull request.
+
 ## License

 This repository is licensed under the [Apache-2.0 License](LICENSE).
--- a/README_zh.md
+++ b/README_zh.md
@@ -8,6 +8,7 @@
 [![GitHub pull request](https://img.shields.io/badge/PRs-welcome-blue)](https://github.com/hiyouga/LLaMA-Factory/pulls)
 [![Discord](https://dcbadge.vercel.app/api/server/c2EPEt5NU?compact=true&style=flat)](https://discord.gg/c2EPEt5NU)
 [![Spaces](https://img.shields.io/badge/🤗-Open%20In%20Spaces-blue)](https://huggingface.co/spaces/hiyouga/LLaMA-Board)
+[![Studios](https://img.shields.io/badge/ModelScope-Open%20In%20Studios-blue)](https://modelscope.cn/studios/hiyouga/LLaMA-Board)

 👋 加入我们的[微信群](assets/wechat.jpg)。

@@ -15,7 +16,7 @@

 ## LLaMA Board: 通过一站式网页界面快速上手 LLaMA Factory

-通过 **[🤗 Spaces](https://huggingface.co/spaces/hiyouga/LLaMA-Board)** 预览 LLaMA Board。
+通过 **[🤗 Spaces](https://huggingface.co/spaces/hiyouga/LLaMA-Board)** 或 **[ModelScope](https://modelscope.cn/studios/hiyouga/LLaMA-Board)** 预览 LLaMA Board。

 使用 `CUDA_VISIBLE_DEVICES=0 python src/train_web.py` 启动 LLaMA Board。（该模式目前仅支持单卡训练）

@@ -23,6 +24,31 @@

 https://github.com/hiyouga/LLaMA-Factory/assets/16256802/6ba60acc-e2e2-4bec-b846-2d88920d5ba1

+## 目录
+
+- [性能指标](#性能指标)
+- [更新日志](#更新日志)
+- [模型](#模型)
+- [训练方法](#训练方法)
+- [数据集](#数据集)
+- [软件依赖](#软件依赖)
+- [如何使用](#如何使用)
+- [使用了 LLaMA Factory 的项目](#使用了-llama-factory-的项目)
+- [协议](#协议)
+- [引用](#引用)
+- [致谢](#致谢)
+
+## 性能指标
+
+与 ChatGLM 官方的 [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ptuning) 微调相比，LLaMA-Factory 的 LoRA 微调提供了 **3.7 倍**的加速比，同时在广告文案生成任务上取得了更高的 Rouge 分数。结合 4 比特量化技术，LLaMA-Factory 的 QLoRA 微调进一步降低了 GPU 显存消耗。
+
+![benchmark](assets/benchmark.svg)
+
+- **Training Speed**: 训练阶段每秒处理的样本数量。（批处理大小=4，截断长度=1024）
+- **Rouge Score**: [广告文案生成](https://aclanthology.org/D19-1321.pdf)任务验证集上的 Rouge-2 分数。（批处理大小=4，截断长度=1024）
+- **GPU Memory**: 4 比特量化训练的 GPU 显存峰值。（批处理大小=1，截断长度=1024）
+- 我们在 ChatGLM 的 P-Tuning 中采用 `pre_seq_len=128`，在 LLaMA-Factory 的 LoRA 微调中采用 `lora_rank=32`。
+
 ## 更新日志

 [23/10/21] 我们支持了 **[NEFTune](https://arxiv.org/abs/2310.05914)** 训练技巧。请使用 `--neft_alpha` 参数启用 NEFTune，例如 `--neft_alpha 5`。
@@ -288,13 +314,19 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
    --per_device_train_batch_size 2 \
    --gradient_accumulation_steps 4 \
    --lr_scheduler_type cosine \
+    --top_k 0 \
+    --top_p 0.9 \
    --logging_steps 10 \
    --save_steps 1000 \
    --learning_rate 1e-5 \
    --num_train_epochs 1.0 \
-    --plot_loss
+    --plot_loss \
+    --fp16
 ```

+> [!WARNING]
+> 如果使用 fp16 精度进行 LLaMA-2 模型的 PPO 训练，请使用 `--per_device_train_batch_size=1`。
+
 #### DPO 训练

 ```bash
@@ -390,7 +422,7 @@ deepspeed --num_gpus 8 --master_port=9901 src/train_bash.py \

 </details>

-### 导出微调后的完整模型
+### 合并 LoRA 权重并导出完整模型

 ```bash
 python src/export_model.py \
@@ -411,7 +443,7 @@ python src/api_demo.py \
    --checkpoint_dir path_to_checkpoint
 ```

-> [!NOTE]
+> [!TIP]
 > 关于 API 文档请见 `http://localhost:8000/docs`。

 ### 命令行测试
@@ -463,10 +495,14 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
    --output_dir path_to_predict_result \
    --per_device_eval_batch_size 8 \
    --max_samples 100 \
-    --predict_with_generate
+    --predict_with_generate \
+    --fp16
 ```

-> [!NOTE]
+> [!WARNING]
+> 如果使用 fp16 精度进行 LLaMA-2 模型的预测，请使用 `--per_device_eval_batch_size=1`。
+
+> [!TIP]
 > 我们建议在量化模型的预测中使用 `--per_device_eval_batch_size=1` 和 `--max_target_length 128`。

 ## 使用了 LLaMA Factory 的项目
@@ -476,6 +512,9 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
 - **[Sunsimiao](https://github.com/thomas-yanxin/Sunsimiao)**: 孙思邈中文医疗大模型 Sumsimiao，基于 Baichuan-7B 和 ChatGLM-6B 在中文医疗数据上微调而得。
 - **[CareGPT](https://github.com/WangRongsheng/CareGPT)**: 医疗大模型项目 CareGPT，基于 LLaMA2-7B 和 Baichuan-13B 在中文医疗数据上微调而得。

+> [!TIP]
+> 如果您有项目希望添加至上述列表，请通过邮件联系或者创建一个 PR。
+
 ## 协议

 本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源。
--- a/assets/benchmark.svg
+++ b/assets/benchmark.svg
--- a/data/wiki_demo.txt
+++ b/data/wiki_demo.txt
@@ -1,50 +0,0 @@
-Machine learning (ML) is a field devoted to understanding and building methods that let machines "learn" – that is, methods that leverage data to improve computer performance on some set of tasks.
-Machine learning algorithms build a model based on sample data, known as training data, in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as in medicine, email filtering, speech recognition, agriculture, and computer vision, where it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.
-A subset of machine learning is closely related to computational statistics, which focuses on making predictions using computers, but not all machine learning is statistical learning. The study of mathematical optimization delivers methods, theory and application domains to the field of machine learning. Data mining is a related field of study, focusing on exploratory data analysis through unsupervised learning.
-Some implementations of machine learning use data and neural networks in a way that mimics the working of a biological brain.
-In its application across business problems, machine learning is also referred to as predictive analytics.
-Learning algorithms work on the basis that strategies, algorithms, and inferences that worked well in the past are likely to continue working well in the future. These inferences can sometimes be obvious, such as "since the sun rose every morning for the last 10,000 days, it will probably rise tomorrow morning as well". Other times, they can be more nuanced, such as "X% of families have geographically separate species with color variants, so there is a Y% chance that undiscovered black swans exist".
-Machine learning programs can perform tasks without being explicitly programmed to do so. It involves computers learning from data provided so that they carry out certain tasks. For simple tasks assigned to computers, it is possible to program algorithms telling the machine how to execute all steps required to solve the problem at hand; on the computer's part, no learning is needed. For more advanced tasks, it can be challenging for a human to manually create the needed algorithms. In practice, it can turn out to be more effective to help the machine develop its own algorithm, rather than having human programmers specify every needed step.
-The discipline of machine learning employs various approaches to teach computers to accomplish tasks where no fully satisfactory algorithm is available. In cases where vast numbers of potential answers exist, one approach is to label some of the correct answers as valid. This can then be used as training data for the computer to improve the algorithm(s) it uses to determine correct answers. For example, to train a system for the task of digital character recognition, the MNIST dataset of handwritten digits has often been used.
-The term machine learning was coined in 1959 by Arthur Samuel, an IBM employee and pioneer in the field of computer gaming and artificial intelligence. The synonym self-teaching computers was also used in this time period.
-By the early 1960s an experimental "learning machine" with punched tape memory, called Cybertron, had been developed by Raytheon Company to analyze sonar signals, electrocardiograms, and speech patterns using rudimentary reinforcement learning. It was repetitively "trained" by a human operator/teacher to recognize patterns and equipped with a "goof" button to cause it to re-evaluate incorrect decisions. A representative book on research into machine learning during the 1960s was Nilsson's book on Learning Machines, dealing mostly with machine learning for pattern classification. Interest related to pattern recognition continued into the 1970s, as described by Duda and Hart in 1973. In 1981 a report was given on using teaching strategies so that a neural network learns to recognize 40 characters (26 letters, 10 digits, and 4 special symbols) from a computer terminal.
-Tom M. Mitchell provided a widely quoted, more formal definition of the algorithms studied in the machine learning field: "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E." This definition of the tasks in which machine learning is concerned offers a fundamentally operational definition rather than defining the field in cognitive terms. This follows Alan Turing's proposal in his paper "Computing Machinery and Intelligence", in which the question "Can machines think?" is replaced with the question "Can machines do what we (as thinking entities) can do?".
-Modern-day machine learning has two objectives, one is to classify data based on models which have been developed, the other purpose is to make predictions for future outcomes based on these models. A hypothetical algorithm specific to classifying data may use computer vision of moles coupled with supervised learning in order to train it to classify the cancerous moles. A machine learning algorithm for stock trading may inform the trader of future potential predictions.
-As a scientific endeavor, machine learning grew out of the quest for artificial intelligence (AI). In the early days of AI as an academic discipline, some researchers were interested in having machines learn from data. They attempted to approach the problem with various symbolic methods, as well as what were then termed "neural networks"; these were mostly perceptrons and other models that were later found to be reinventions of the generalized linear models of statistics. Probabilistic reasoning was also employed, especially in automated medical diagnosis.: 488 
-However, an increasing emphasis on the logical, knowledge-based approach caused a rift between AI and machine learning. Probabilistic systems were plagued by theoretical and practical problems of data acquisition and representation.: 488  By 1980, expert systems had come to dominate AI, and statistics was out of favor. Work on symbolic/knowledge-based learning did continue within AI, leading to inductive logic programming, but the more statistical line of research was now outside the field of AI proper, in pattern recognition and information retrieval.: 708–710, 755  Neural networks research had been abandoned by AI and computer science around the same time. This line, too, was continued outside the AI/CS field, as "connectionism", by researchers from other disciplines including Hopfield, Rumelhart, and Hinton. Their main success came in the mid-1980s with the reinvention of backpropagation.: 25 
-Machine learning (ML), reorganized and recognized as its own field, started to flourish in the 1990s. The field changed its goal from achieving artificial intelligence to tackling solvable problems of a practical nature. It shifted focus away from the symbolic approaches it had inherited from AI, and toward methods and models borrowed from statistics, fuzzy logic, and probability theory.
-Machine learning and data mining often employ the same methods and overlap significantly, but while machine learning focuses on prediction, based on known properties learned from the training data, data mining focuses on the discovery of (previously) unknown properties in the data (this is the analysis step of knowledge discovery in databases). Data mining uses many machine learning methods, but with different goals; on the other hand, machine learning also employs data mining methods as "unsupervised learning" or as a preprocessing step to improve learner accuracy. Much of the confusion between these two research communities (which do often have separate conferences and separate journals, ECML PKDD being a major exception) comes from the basic assumptions they work with: in machine learning, performance is usually evaluated with respect to the ability to reproduce known knowledge, while in knowledge discovery and data mining (KDD) the key task is the discovery of previously unknown knowledge. Evaluated with respect to known knowledge, an uninformed (unsupervised) method will easily be outperformed by other supervised methods, while in a typical KDD task, supervised methods cannot be used due to the unavailability of training data.
-Machine learning also has intimate ties to optimization: many learning problems are formulated as minimization of some loss function on a training set of examples. Loss functions express the discrepancy between the predictions of the model being trained and the actual problem instances (for example, in classification, one wants to assign a label to instances, and models are trained to correctly predict the pre-assigned labels of a set of examples).
-The difference between optimization and machine learning arises from the goal of generalization: while optimization algorithms can minimize the loss on a training set, machine learning is concerned with minimizing the loss on unseen samples. Characterizing the generalization of various learning algorithms is an active topic of current research, especially for deep learning algorithms.
-Machine learning and statistics are closely related fields in terms of methods, but distinct in their principal goal: statistics draws population inferences from a sample, while machine learning finds generalizable predictive patterns. According to Michael I. Jordan, the ideas of machine learning, from methodological principles to theoretical tools, have had a long pre-history in statistics. He also suggested the term data science as a placeholder to call the overall field.
-Leo Breiman distinguished two statistical modeling paradigms: data model and algorithmic model, wherein "algorithmic model" means more or less the machine learning algorithms like Random Forest.
-Some statisticians have adopted methods from machine learning, leading to a combined field that they call statistical learning.
-Analytical and computational techniques derived from deep-rooted physics of disordered systems can be extended to large-scale problems, including machine learning, e.g., to analyze the weight space of deep neural networks. Statistical physics is thus finding applications in the area of medical diagnostics.
-A core objective of a learner is to generalize from its experience. Generalization in this context is the ability of a learning machine to perform accurately on new, unseen examples/tasks after having experienced a learning data set. The training examples come from some generally unknown probability distribution (considered representative of the space of occurrences) and the learner has to build a general model about this space that enables it to produce sufficiently accurate predictions in new cases.
-The computational analysis of machine learning algorithms and their performance is a branch of theoretical computer science known as computational learning theory via the Probably Approximately Correct Learning (PAC) model. Because training sets are finite and the future is uncertain, learning theory usually does not yield guarantees of the performance of algorithms. Instead, probabilistic bounds on the performance are quite common. The bias–variance decomposition is one way to quantify generalization error.
-For the best performance in the context of generalization, the complexity of the hypothesis should match the complexity of the function underlying the data. If the hypothesis is less complex than the function, then the model has under fitted the data. If the complexity of the model is increased in response, then the training error decreases. But if the hypothesis is too complex, then the model is subject to overfitting and generalization will be poorer.
-In addition to performance bounds, learning theorists study the time complexity and feasibility of learning. In computational learning theory, a computation is considered feasible if it can be done in polynomial time. There are two kinds of time complexity results: Positive results show that a certain class of functions can be learned in polynomial time. Negative results show that certain classes cannot be learned in polynomial time.
-Machine learning approaches are traditionally divided into three broad categories, which correspond to learning paradigms, depending on the nature of the "signal" or "feedback" available to the learning system:
-Supervised learning: The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that maps inputs to outputs.
-Unsupervised learning: No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end (feature learning).
-Reinforcement learning: A computer program interacts with a dynamic environment in which it must perform a certain goal (such as driving a vehicle or playing a game against an opponent). As it navigates its problem space, the program is provided feedback that's analogous to rewards, which it tries to maximize. Although each algorithm has advantages and limitations, no single algorithm works for all problems.
-Supervised learning algorithms build a mathematical model of a set of data that contains both the inputs and the desired outputs. The data is known as training data, and consists of a set of training examples. Each training example has one or more inputs and the desired output, also known as a supervisory signal. In the mathematical model, each training example is represented by an array or vector, sometimes called a feature vector, and the training data is represented by a matrix. Through iterative optimization of an objective function, supervised learning algorithms learn a function that can be used to predict the output associated with new inputs. An optimal function will allow the algorithm to correctly determine the output for inputs that were not a part of the training data. An algorithm that improves the accuracy of its outputs or predictions over time is said to have learned to perform that task.
-Types of supervised-learning algorithms include active learning, classification and regression. Classification algorithms are used when the outputs are restricted to a limited set of values, and regression algorithms are used when the outputs may have any numerical value within a range. As an example, for a classification algorithm that filters emails, the input would be an incoming email, and the output would be the name of the folder in which to file the email.
-Similarity learning is an area of supervised machine learning closely related to regression and classification, but the goal is to learn from examples using a similarity function that measures how similar or related two objects are. It has applications in ranking, recommendation systems, visual identity tracking, face verification, and speaker verification.
-Unsupervised learning algorithms take a set of data that contains only inputs, and find structure in the data, like grouping or clustering of data points. The algorithms, therefore, learn from test data that has not been labeled, classified or categorized. Instead of responding to feedback, unsupervised learning algorithms identify commonalities in the data and react based on the presence or absence of such commonalities in each new piece of data. A central application of unsupervised learning is in the field of density estimation in statistics, such as finding the probability density function. Though unsupervised learning encompasses other domains involving summarizing and explaining data features. Unsupervised learning algorithms streamlined the process of survey and graph large indel based haplotypes of a gene of interest from pan-genome. 
-Cluster analysis is the assignment of a set of observations into subsets (called clusters) so that observations within the same cluster are similar according to one or more predesignated criteria, while observations drawn from different clusters are dissimilar. Different clustering techniques make different assumptions on the structure of the data, often defined by some similarity metric and evaluated, for example, by internal compactness, or the similarity between members of the same cluster, and separation, the difference between clusters. Other methods are based on estimated density and graph connectivity.
-Semi-supervised learning falls between unsupervised learning (without any labeled training data) and supervised learning (with completely labeled training data). Some of the training examples are missing training labels, yet many machine-learning researchers have found that unlabeled data, when used in conjunction with a small amount of labeled data, can produce a considerable improvement in learning accuracy.
-In weakly supervised learning, the training labels are noisy, limited, or imprecise; however, these labels are often cheaper to obtain, resulting in larger effective training sets.
-Reinforcement learning is an area of machine learning concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. Due to its generality, the field is studied in many other disciplines, such as game theory, control theory, operations research, information theory, simulation-based optimization, multi-agent systems, swarm intelligence, statistics and genetic algorithms. In machine learning, the environment is typically represented as a Markov decision process (MDP). Many reinforcements learning algorithms use dynamic programming techniques. Reinforcement learning algorithms do not assume knowledge of an exact mathematical model of the MDP and are used when exact models are infeasible. Reinforcement learning algorithms are used in autonomous vehicles or in learning to play a game against a human opponent.
-Dimensionality reduction is a process of reducing the number of random variables under consideration by obtaining a set of principal variables. In other words, it is a process of reducing the dimension of the feature set, also called the "number of features". Most of the dimensionality reduction techniques can be considered as either feature elimination or extraction. One of the popular methods of dimensionality reduction is principal component analysis (PCA). PCA involves changing higher-dimensional data (e.g., 3D) to a smaller space (e.g., 2D). This results in a smaller dimension of data (2D instead of 3D), while keeping all original variables in the model without changing the data. The manifold hypothesis proposes that high-dimensional data sets lie along low-dimensional manifolds, and many dimensionality reduction techniques make this assumption, leading to the area of manifold learning and manifold regularization.
-Although machine learning has been transformative in some fields, machine-learning programs often fail to deliver expected results. Reasons for this are numerous: lack of (suitable) data, lack of access to the data, data bias, privacy problems, badly chosen tasks and algorithms, wrong tools and people, lack of resources, and evaluation problems.
-In 2018, a self-driving car from Uber failed to detect a pedestrian, who was killed after a collision. Attempts to use machine learning in healthcare with the IBM Watson system failed to deliver even after years of time and billions of dollars invested.
-Machine learning has been used as a strategy to update the evidence related to a systematic review and increased reviewer burden related to the growth of biomedical literature. While it has improved with training sets, it has not yet developed sufficiently to reduce the workload burden without limiting the necessary sensitivity for the findings research themselves.
-Machine learning approaches in particular can suffer from different data biases. A machine learning system trained specifically on current customers may not be able to predict the needs of new customer groups that are not represented in the training data. When trained on human-made data, machine learning is likely to pick up the constitutional and unconscious biases already present in society. Language models learned from data have been shown to contain human-like biases. Machine learning systems used for criminal risk assessment have been found to be biased against black people. In 2015, Google photos would often tag black people as gorillas, and in 2018 this still was not well resolved, but Google reportedly was still using the workaround to remove all gorillas from the training data, and thus was not able to recognize real gorillas at all. Similar issues with recognizing non-white people have been found in many other systems. In 2016, Microsoft tested a chatbot that learned from Twitter, and it quickly picked up racist and sexist language. Because of such challenges, the effective use of machine learning may take longer to be adopted in other domains. Concern for fairness in machine learning, that is, reducing bias in machine learning and propelling its use for human good is increasingly expressed by artificial intelligence scientists, including Fei-Fei Li, who reminds engineers that "There's nothing artificial about AI...It's inspired by people, it's created by people, and—most importantly—it impacts people. It is a powerful tool we are only just beginning to understand, and that is a profound responsibility."
-Learners can also disappoint by "learning the wrong lesson". A toy example is that an image classifier trained only on pictures of brown horses and black cats might conclude that all brown patches are likely to be horses. A real-world example is that, unlike humans, current image classifiers often do not primarily make judgments from the spatial relationship between components of the picture, and they learn relationships between pixels that humans are oblivious to, but that still correlate with images of certain types of real objects. Modifying these patterns on a legitimate image can result in "adversarial" images that the system misclassifies.
-Adversarial vulnerabilities can also result in nonlinear systems, or from non-pattern perturbations. Some systems are so brittle that changing a single adversarial pixel predictably induces misclassification.[citation needed] Machine learning models are often vulnerable to manipulation and/or evasion via adversarial machine learning.
-Researchers have demonstrated how backdoors can be placed undetectably into classifying (e.g., for categories "spam" and well-visible "not spam" of posts) machine learning models which are often developed and/or trained by third parties. Parties can change the classification of any input, including in cases for which a type of data/software transparency is provided, possibly including white-box access.
-Machine learning poses a host of ethical questions. Systems that are trained on datasets collected with biases may exhibit these biases upon use (algorithmic bias), thus digitizing cultural prejudices. For example, in 1988, the UK's Commission for Racial Equality found that St. George's Medical School had been using a computer program trained from data of previous admissions staff and this program had denied nearly 60 candidates who were found to be either women or had non-European sounding names. Using job hiring data from a firm with racist hiring policies may lead to a machine learning system duplicating the bias by scoring job applicants by similarity to previous successful applicants. Responsible collection of data and documentation of algorithmic rules used by a system thus is a critical part of machine learning.
-AI can be well-equipped to make decisions in technical fields, which rely heavily on data and historical information. These decisions rely on the objectivity and logical reasoning. Because human languages contain biases, machines trained on language corpora will necessarily also learn these biases.
-Other forms of ethical challenges, not related to personal biases, are seen in health care. There are concerns among health care professionals that these systems might not be designed in the public's interest but as income-generating machines. This is especially true in the United States where there is a long-standing ethical dilemma of improving health care, but also increase profits. For example, the algorithms could be designed to provide patients with unnecessary tests or medication in which the algorithm's proprietary owners hold stakes. There is potential for machine learning in health care to provide professionals an additional tool to diagnose, medicate, and plan recovery paths for patients, but this requires these biases to be mitigated.
-Since the 2010s, advances in both machine learning algorithms and computer hardware have led to more efficient methods for training deep neural networks (a particular narrow subdomain of machine learning) that contain many layers of non-linear hidden units. By 2019, graphic processing units (GPUs), often with AI-specific enhancements, had displaced CPUs as the dominant method of training large-scale commercial cloud AI. OpenAI estimated the hardware computing used in the largest deep learning projects from AlexNet (2012) to AlphaZero (2017), and found a 300,000-fold increase in the amount of compute required, with a doubling-time trendline of 3.4 months.
--- a/data/wiki_demo.txt.REMOVED.git-id
+++ b/data/wiki_demo.txt.REMOVED.git-id
@@ -0,0 +1 @@
+c9cf509b7fdac5490cfd6dae72c2d7b8a60af6cb
--- a/src/llmtuner/init.py
+++ b/src/llmtuner/init.py
@@ -7,4 +7,4 @@ from llmtuner.train import export_model, run_exp
 from llmtuner.webui import create_ui, create_web_demo


-__version__ = "0.3.0"
+__version__ = "0.3.2"
--- a/src/llmtuner/data/loader.py
+++ b/src/llmtuner/data/loader.py
@@ -60,9 +60,12 @@ def get_dataset(
            split=data_args.split,
            cache_dir=model_args.cache_dir,
            token=model_args.hf_hub_token,
-            streaming=data_args.streaming
+            streaming=(data_args.streaming and (dataset_attr.load_from != "file"))
        )

+        if data_args.streaming and (dataset_attr.load_from == "file"):
+            dataset = dataset.to_iterable_dataset() # TODO: add num shards parameter
+
        if max_samples is not None: # truncate dataset
            dataset = dataset.select(range(min(len(dataset), max_samples)))

--- a/src/llmtuner/data/template.py
+++ b/src/llmtuner/data/template.py
@@ -114,7 +114,7 @@ class Template:
            else:
                prefix_ids = sep_ids + bos_ids

-            query_ids = self._convert_inputs_to_ids(tokenizer, context=self.prompt, query=query, idx=str(turn_idx))
+            query_ids = self._convert_inputs_to_ids(tokenizer, context=self.prompt, query=query, idx=str(turn_idx+1))
            resp_ids = self._convert_inputs_to_ids(tokenizer, context=[resp])
            encoded_pairs.append((prefix_ids + query_ids, resp_ids + eos_ids))
        return encoded_pairs
@@ -350,6 +350,37 @@ register_template(
    prefix=[
        {"token": "[gMASK]"},
        {"token": "sop"},
+        {"token": "<|system|>"},
+        "\n",
+        "{{system}}"
+    ],
+    prompt=[
+        {"token": "<|user|>"},
+        "\n",
+        "{{query}}",
+        {"token": "<|assistant|>"},
+        "\n" # add an extra newline to avoid error in ChatGLM's process_response method
+    ],
+    system=(
+        "You are ChatGLM3, a large language model trained by Zhipu.AI. "
+        "Follow the user's instructions carefully. Respond using markdown."
+    ),
+    sep=[],
+    stop_words=[
+        "<|user|>",
+        "<|observation|>"
+    ],
+    efficient_eos=True
+)
+
+
+register_template(
+    name="chatglm3_raw", # the raw template for tool tuning
+    prefix=[
+        {"token": "[gMASK]"},
+        {"token": "sop"},
+        {"token": "<|system|>"},
+        "\n",
        "{{system}}"
    ],
    prompt=[
@@ -358,7 +389,10 @@ register_template(
        "{{query}}",
        {"token": "<|assistant|>"}
    ],
-    system="",
+    system=(
+        "You are ChatGLM3, a large language model trained by Zhipu.AI. "
+        "Follow the user's instructions carefully. Respond using markdown."
+    ),
    sep=[],
    stop_words=[
        "<|user|>",
@@ -494,7 +528,9 @@ register_template(
        "[INST] {{query}} [/INST]"
    ],
    system="",
-    sep=[]
+    sep=[
+        " "
+    ]
 )


--- a/src/llmtuner/eval/evaluator.py
+++ b/src/llmtuner/eval/evaluator.py
@@ -3,6 +3,7 @@
 import os
 import json
 import torch
+import inspect
 import tiktoken
 import numpy as np
 from tqdm import tqdm, trange
@@ -45,13 +46,18 @@ class Evaluator:
        return [chr(ord("A") + offset.item()) for offset in torch.argmax(choice_probs, dim=-1)]

    def eval(self) -> None:
+        if "token" in inspect.signature(cached_file).parameters:
+            kwargs = {"token": self.model_args.hf_hub_token}
+        elif "use_auth_token" in inspect.signature(cached_file).parameters: # for transformers==4.31.0
+            kwargs = {"use_auth_token": self.model_args.hf_hub_token}
+
        mapping = cached_file(
            path_or_repo_id = os.path.join(self.eval_args.task_dir, self.eval_args.task),
            filename="mapping.json",
            cache_dir=self.model_args.cache_dir,
-            token=self.model_args.hf_hub_token,
-            revision=self.model_args.model_revision
+            **kwargs
        )
+
        with open(mapping, "r", encoding="utf-8") as f:
            categorys: Dict[str, Dict[str, str]] = json.load(f)

@@ -62,7 +68,9 @@ class Evaluator:
            dataset = load_dataset(
                path=os.path.join(self.eval_args.task_dir, self.eval_args.task),
                name=subject,
-                download_mode="force_redownload"
+                cache_dir=self.model_args.cache_dir,
+                download_mode=self.eval_args.download_mode,
+                token=self.model_args.hf_hub_token
            )
            pbar.set_postfix_str(categorys[subject]["name"])
            inputs, outputs, labels = [], [], []
--- a/src/llmtuner/extras/misc.py
+++ b/src/llmtuner/extras/misc.py
@@ -16,7 +16,10 @@ try:
    _is_bf16_available = is_torch_bf16_gpu_available() or is_torch_bf16_cpu_available()
 except ImportError:
    _is_fp16_available = torch.cuda.is_available()
-    _is_bf16_available = torch.cuda.is_bf16_supported()
+    try:
+        _is_bf16_available = torch.cuda.is_bf16_supported()
+    except:
+        _is_bf16_available = False

 if TYPE_CHECKING:
    from transformers import HfArgumentParser
@@ -66,8 +69,7 @@ def count_parameters(model: torch.nn.Module) -> Tuple[int, int]:

 def get_current_device() -> str:
    import accelerate
-    from accelerate import Accelerator
-    dummy_accelerator = Accelerator()
+    dummy_accelerator = accelerate.Accelerator()
    if accelerate.utils.is_xpu_available():
        return "xpu:{}".format(dummy_accelerator.local_process_index)
    else:
--- a/src/llmtuner/extras/packages.py
+++ b/src/llmtuner/extras/packages.py
@@ -18,8 +18,8 @@ _flash_attn2_available = is_package_available("flash_attn") and get_package_vers
 _jieba_available = is_package_available("jieba")
 _matplotlib_available = is_package_available("matplotlib")
 _nltk_available = is_package_available("nltk")
-_rouge_available = is_package_available("rouge-chinese")
-_starlette_available = is_package_available("sse-starlette")
+_rouge_available = is_package_available("rouge_chinese")
+_starlette_available = is_package_available("sse_starlette")
 _uvicorn_available = is_package_available("uvicorn")


--- a/src/llmtuner/hparams/finetuning_args.py
+++ b/src/llmtuner/hparams/finetuning_args.py
@@ -8,10 +8,6 @@ class FreezeArguments:
    r"""
    Arguments pertaining to the freeze (partial-parameter) training.
    """
-    num_layer_trainable: Optional[int] = field(
-        default=3,
-        metadata={"help": "Number of trainable layers for partial-parameter (freeze) fine-tuning."}
-    )
    name_module_trainable: Optional[str] = field(
        default="mlp",
        metadata={"help": "Name of trainable modules for partial-parameter (freeze) fine-tuning. \
@@ -22,6 +18,10 @@ class FreezeArguments:
                  Phi-1.5 choices: [\"mlp\", \"mixer\"], \
                  Others choices: the same as LLaMA."}
    )
+    num_layer_trainable: Optional[int] = field(
+        default=3,
+        metadata={"help": "The number of trainable layers for partial-parameter (freeze) fine-tuning."}
+    )


@dataclass
@@ -29,9 +29,9 @@ class LoraArguments:
    r"""
    Arguments pertaining to the LoRA training.
    """
-    lora_rank: Optional[int] = field(
-        default=8,
-        metadata={"help": "The intrinsic dimension for LoRA fine-tuning."}
+    additional_target: Optional[str] = field(
+        default=None,
+        metadata={"help": "Name(s) of modules apart from LoRA layers to be set as trainable and saved in the final checkpoint."}
    )
    lora_alpha: Optional[float] = field(
        default=None,
@@ -41,6 +41,10 @@ class LoraArguments:
        default=0.1,
        metadata={"help": "Dropout rate for the LoRA fine-tuning."}
    )
+    lora_rank: Optional[int] = field(
+        default=8,
+        metadata={"help": "The intrinsic dimension for LoRA fine-tuning."}
+    )
    lora_target: Optional[str] = field(
        default=None,
        metadata={"help": "Name(s) of target modules to apply LoRA. Use commas to separate multiple modules. \
@@ -51,10 +55,6 @@ class LoraArguments:
                  Phi-1.5 choices: [\"Wqkv\", \"out_proj\", \"fc1\", \"fc2\"], \
                  Others choices: the same as LLaMA."}
    )
-    additional_target: Optional[str] = field(
-        default=None,
-        metadata={"help": "Name(s) of modules apart from LoRA layers to be set as trainable and saved in the final checkpoint."}
-    )
    resume_lora_training: Optional[bool] = field(
        default=True,
        metadata={"help": "Whether to resume training from the last LoRA weights or create new weights after merging them."}
@@ -70,9 +70,17 @@ class RLHFArguments:
        default=0.1,
        metadata={"help": "The beta parameter for the DPO loss."}
    )
+    ppo_buffer_size: Optional[int] = field(
+        default=1,
+        metadata={"help": "The number of mini-batches to make experience buffer in a PPO optimization step."}
+    )
+    ppo_epochs: Optional[int] = field(
+        default=4,
+        metadata={"help": "The number of epochs to perform in a PPO optimization step."}
+    )
    ppo_logger: Optional[str] = field(
        default=None,
-        metadata={"help": "Log with either 'wandb' or 'tensorboard' in PPO training."}
+        metadata={"help": "Log with either \"wandb\" or \"tensorboard\" in PPO training."}
    )
    ppo_score_norm: Optional[bool] = field(
        default=False,
--- a/src/llmtuner/model/init.py
+++ b/src/llmtuner/model/init.py
@@ -2,4 +2,4 @@

 from llmtuner.model.loader import load_model_and_tokenizer
 from llmtuner.model.parser import get_train_args, get_infer_args, get_eval_args
-from llmtuner.model.utils import dispatch_model, generate_model_card, load_valuehead_params
+from llmtuner.model.utils import dispatch_model, get_modelcard_args, load_valuehead_params
--- a/src/llmtuner/model/adapter.py
+++ b/src/llmtuner/model/adapter.py
@@ -65,7 +65,12 @@ def init_adapter(
        checkpoint_to_resume = None

        if model_args.checkpoint_dir is not None:
-            if is_trainable and finetuning_args.resume_lora_training:
+            is_mergeable = True
+            if getattr(model, "quantization_method", None) == "gptq":
+                assert len(model_args.checkpoint_dir) == 1, "GPTQ quantized model only accepts a single checkpoint."
+                is_mergeable = False
+
+            if (is_trainable and finetuning_args.resume_lora_training) or (not is_mergeable):
                checkpoints_to_merge, checkpoint_to_resume = model_args.checkpoint_dir[:-1], model_args.checkpoint_dir[-1]
            else:
                checkpoints_to_merge = model_args.checkpoint_dir
--- a/src/llmtuner/model/loader.py
+++ b/src/llmtuner/model/loader.py
@@ -1,4 +1,3 @@
-import os
 import math
 import torch
 from types import MethodType
@@ -202,6 +201,8 @@ def load_model_and_tokenizer(
    # Prepare model with valuehead for RLHF
    if stage in ["rm", "ppo"]:
        model: "AutoModelForCausalLMWithValueHead" = AutoModelForCausalLMWithValueHead.from_pretrained(model)
+        setattr(model, "_keys_to_ignore_on_save", [name for name, _ in model.named_parameters() if "pretrained_model" in name])
+        setattr(model, "tie_weights", MethodType(lambda _: None, model)) # use empty method
        vhead_path = (
            model_args.checkpoint_dir[-1] if model_args.checkpoint_dir is not None else model_args.model_name_or_path
        )
--- a/src/llmtuner/model/parser.py
+++ b/src/llmtuner/model/parser.py
@@ -40,6 +40,18 @@ _EVAL_CLS = Tuple[
 ]


+def _verify_model_args(model_args: "ModelArguments", finetuning_args: "FinetuningArguments") -> None:
+    if model_args.quantization_bit is not None and finetuning_args.finetuning_type != "lora":
+        raise ValueError("Quantization is only compatible with the LoRA method.")
+
+    if (
+        model_args.checkpoint_dir is not None
+        and len(model_args.checkpoint_dir) != 1
+        and finetuning_args.finetuning_type != "lora"
+    ):
+        raise ValueError("Multiple checkpoints are only available for LoRA tuning.")
+
+
 def parse_train_args(args: Optional[Dict[str, Any]] = None) -> _TRAIN_CLS:
    parser = HfArgumentParser(_TRAIN_ARGS)
    return parse_args(parser, args)
@@ -81,19 +93,14 @@ def get_train_args(args: Optional[Dict[str, Any]] = None) -> _TRAIN_CLS:
    if finetuning_args.stage == "sft" and training_args.do_predict and not training_args.predict_with_generate:
        raise ValueError("Please enable `predict_with_generate` to save model predictions.")

-    if finetuning_args.stage in ["rm", "ppo"]:
-        if training_args.resume_from_checkpoint is not None:
-            raise ValueError("RM and PPO stages do not support `resume_from_checkpoint`.")
-        if training_args.load_best_model_at_end:
-            raise ValueError("RM and PPO stages do not support `load_best_model_at_end`.")
+    if finetuning_args.stage in ["rm", "ppo"] and training_args.load_best_model_at_end:
+        raise ValueError("RM and PPO stages do not support `load_best_model_at_end`.")

    if finetuning_args.stage == "ppo" and not training_args.do_train:
        raise ValueError("PPO training does not support evaluation, use the SFT stage to evaluate models.")

-    if finetuning_args.stage in ["rm", "dpo"]:
-        for dataset_attr in data_args.dataset_list:
-            if not dataset_attr.ranking:
-                raise ValueError("Please use ranked datasets for reward modeling or DPO training.")
+    if finetuning_args.stage in ["rm", "dpo"] and (not all([data_attr.ranking for data_attr in data_args.dataset_list])):
+        raise ValueError("Please use ranked datasets for reward modeling or DPO training.")

    if finetuning_args.stage == "ppo" and model_args.shift_attn:
        raise ValueError("PPO training is incompatible with S^2-Attn.")
@@ -107,15 +114,7 @@ def get_train_args(args: Optional[Dict[str, Any]] = None) -> _TRAIN_CLS:
    if training_args.do_train and finetuning_args.finetuning_type == "lora" and finetuning_args.lora_target is None:
        raise ValueError("Please specify `lora_target` in LoRA training.")

-    if model_args.quantization_bit is not None and finetuning_args.finetuning_type != "lora":
-        raise ValueError("Quantization is only compatible with the LoRA method.")
-
-    if (
-        model_args.checkpoint_dir is not None
-        and len(model_args.checkpoint_dir) != 1
-        and finetuning_args.finetuning_type != "lora"
-    ):
-        raise ValueError("Only LoRA tuning accepts multiple checkpoints.")
+    _verify_model_args(model_args, finetuning_args)

    if training_args.do_train and model_args.quantization_bit is not None and (not finetuning_args.upcast_layernorm):
        logger.warning("We recommend enable `upcast_layernorm` in quantized training.")
@@ -154,9 +153,14 @@ def get_train_args(args: Optional[Dict[str, Any]] = None) -> _TRAIN_CLS:
            training_args_dict = training_args.to_dict()
            training_args_dict.update(dict(resume_from_checkpoint=last_checkpoint))
            training_args = Seq2SeqTrainingArguments(**training_args_dict)
-            logger.info(
-                "Resuming from checkpoint. Change `output_dir` or use `overwrite_output_dir` to avoid."
-            )
+            logger.info("Resuming training from {}. Change `output_dir` or use `overwrite_output_dir` to avoid.".format(
+                training_args.resume_from_checkpoint
+            ))
+
+    if finetuning_args.stage in ["rm", "ppo"] and training_args.resume_from_checkpoint is not None:
+        logger.warning("Add {} to `checkpoint_dir` to resume training from checkpoint.".format(
+            training_args.resume_from_checkpoint
+        ))

    # postprocess model_args
    model_args.compute_dtype = (
@@ -183,15 +187,7 @@ def get_infer_args(args: Optional[Dict[str, Any]] = None) -> _INFER_CLS:
    if data_args.template is None:
        raise ValueError("Please specify which `template` to use.")

-    if model_args.quantization_bit is not None and finetuning_args.finetuning_type != "lora":
-        raise ValueError("Quantization is only compatible with the LoRA method.")
-
-    if (
-        model_args.checkpoint_dir is not None
-        and len(model_args.checkpoint_dir) != 1
-        and finetuning_args.finetuning_type != "lora"
-    ):
-        raise ValueError("Only LoRA tuning accepts multiple checkpoints.")
+    _verify_model_args(model_args, finetuning_args)

    return model_args, data_args, finetuning_args, generating_args

@@ -202,8 +198,7 @@ def get_eval_args(args: Optional[Dict[str, Any]] = None) -> _EVAL_CLS:
    if data_args.template is None:
        raise ValueError("Please specify which `template` to use.")

-    if model_args.quantization_bit is not None and finetuning_args.finetuning_type != "lora":
-        raise ValueError("Quantization is only compatible with the LoRA method.")
+    _verify_model_args(model_args, finetuning_args)

    transformers.set_seed(eval_args.seed)

--- a/src/llmtuner/model/utils.py
+++ b/src/llmtuner/model/utils.py
@@ -1,4 +1,5 @@
 import torch
+import inspect
 from typing import TYPE_CHECKING, Any, Dict, List, Optional, Set, Tuple

 from transformers.utils import cached_file
@@ -70,13 +71,14 @@ def find_all_linear_modules(
    return list(module_names)


-def generate_model_card(
+def get_modelcard_args(
    model_args: "ModelArguments",
    data_args: "DataArguments",
    finetuning_args: "FinetuningArguments"
 ) -> Dict[str, Any]:
    return {
        "tasks": "text-generation",
+        "license": "other",
        "finetuned_from": model_args.model_name_or_path,
        "dataset": [dataset.strip() for dataset in data_args.dataset.split(",")],
        "tags": ["llama-factory"] + (["lora"] if finetuning_args.finetuning_type == "lora" else [])
@@ -94,19 +96,35 @@ def load_valuehead_params(
    """
    kwargs = {
        "path_or_repo_id": path_or_repo_id,
-        "cache_dir": model_args.cache_dir,
-        "token": model_args.hf_hub_token
+        "cache_dir": model_args.cache_dir
    }
+
+    if "token" in inspect.signature(cached_file).parameters:
+        kwargs["token"] = model_args.hf_hub_token
+    elif "use_auth_token" in inspect.signature(cached_file).parameters: # for transformers==4.31.0
+        kwargs["use_auth_token"] = model_args.hf_hub_token
+    else:
+        logger.warning("Ignore `hf_hub_token` since matched parameter is not found.")
+
    try:
        vhead_file = cached_file(filename=WEIGHTS_NAME, **kwargs)
-    except:
-        try:
-            vhead_file = cached_file(filename=SAFE_WEIGHTS_NAME, **kwargs)
-        except:
-            logger.warning("Provided path ({}) does not contain valuehead weights.".format(path_or_repo_id))
-            return None
+        return torch.load(vhead_file, map_location="cpu")
+    except Exception as err:
+        logger.info("Failed to load {}: {}".format(WEIGHTS_NAME, str(err)))

-    return torch.load(vhead_file, map_location="cpu")
+    try:
+        from safetensors import safe_open
+        vhead_file = cached_file(filename=SAFE_WEIGHTS_NAME, **kwargs)
+        with safe_open(vhead_file, framework="pt", device="cpu") as f:
+            return {
+                "v_head.summary.weight": f.get_tensor("v_head.summary.weight"),
+                "v_head.summary.bias": f.get_tensor("v_head.summary.bias")
+            }
+    except Exception as err:
+        logger.info("Failed to load {}: {}".format(SAFE_WEIGHTS_NAME, str(err)))
+
+    logger.warning("Provided path ({}) does not contain valuehead weights.".format(path_or_repo_id))
+    return None


 def prepare_model_for_training(
@@ -140,7 +158,7 @@ def prepare_model_for_training(
        model.get_input_embeddings().register_forward_hook(neftune_forward_hook)
        logger.info("Using noisy embedding with alpha={:.2f}".format(finetuning_args.neft_alpha))

-    if use_gradient_checkpointing:
+    if use_gradient_checkpointing and getattr(model, "supports_gradient_checkpointing", False):
        if hasattr(model, "enable_input_require_grads"):
            model.enable_input_require_grads()
        else:
--- a/src/llmtuner/train/dpo/workflow.py
+++ b/src/llmtuner/train/dpo/workflow.py
@@ -1,6 +1,5 @@
 # Inspired by: https://github.com/huggingface/trl/blob/main/examples/research_projects/stack_llama_2/scripts/dpo_llama2.py

-from peft import PeftModel
 from typing import TYPE_CHECKING, Optional, List
 from transformers import Seq2SeqTrainingArguments

@@ -8,10 +7,10 @@ from llmtuner.data import get_dataset, preprocess_dataset, split_dataset
 from llmtuner.extras.constants import IGNORE_INDEX
 from llmtuner.extras.ploting import plot_loss
 from llmtuner.hparams import ModelArguments
-from llmtuner.model import generate_model_card, load_model_and_tokenizer
-from llmtuner.train.utils import create_ref_model
+from llmtuner.model import load_model_and_tokenizer
 from llmtuner.train.dpo.collator import DPODataCollatorWithPadding
 from llmtuner.train.dpo.trainer import CustomDPOTrainer
+from llmtuner.train.utils import create_modelcard_and_push, create_ref_model

 if TYPE_CHECKING:
    from transformers import TrainerCallback
@@ -78,8 +77,4 @@ def run_dpo(
        trainer.save_metrics("eval", metrics)

    # Create model card
-    if training_args.do_train:
-        if training_args.push_to_hub:
-            trainer.push_to_hub(**generate_model_card(model_args, data_args, finetuning_args))
-        else:
-            trainer.create_model_card(**generate_model_card(model_args, data_args, finetuning_args))
+    create_modelcard_and_push(trainer, model_args, data_args, training_args, finetuning_args)
--- a/src/llmtuner/train/ppo/trainer.py
+++ b/src/llmtuner/train/ppo/trainer.py
@@ -74,18 +74,24 @@ class CustomPPOTrainer(PPOTrainer, Trainer):
            else:
                self.reward_model = self.accelerator.prepare_model(self.reward_model, evaluation_mode=True)

-    def ppo_train(self) -> None:
+    def ppo_train(self, resume_from_checkpoint: Optional[str] = None) -> None:
        r"""
        Implements training loop for the PPO stage, like _inner_training_loop() in Huggingface's Trainer.
        """
+        if resume_from_checkpoint is not None:
+            raise ValueError("`resume_from_checkpoint` will be supported in the future version.")
+
        total_train_batch_size = (
-            self.args.per_device_train_batch_size * self.args.gradient_accumulation_steps * self.args.world_size
+            self.args.per_device_train_batch_size
+            * self.args.gradient_accumulation_steps
+            * self.finetuning_args.ppo_buffer_size
+            * self.args.world_size
        )
        if self.args.max_steps > 0:
            num_examples = total_train_batch_size * self.args.max_steps
            num_train_epochs = sys.maxsize
            max_steps = self.args.max_steps
-            steps_in_epoch = self.args.max_steps * self.args.gradient_accumulation_steps
+            steps_in_epoch = self.args.max_steps
        else:
            len_dataloader = len(self.dataloader)
            num_examples = len(self.dataset)
@@ -100,13 +106,16 @@ class CustomPPOTrainer(PPOTrainer, Trainer):

        if self.is_world_process_zero():
            logger.info("***** Running training *****")
-            logger.info(f"  Num examples = {num_examples}")
-            logger.info(f"  Num Epochs = {num_train_epochs}")
-            logger.info(f"  Instantaneous batch size per device = {self.args.per_device_train_batch_size}")
-            logger.info(f"  Total train batch size (w. parallel, distributed & accumulation) = {total_train_batch_size}")
-            logger.info(f"  Gradient Accumulation steps = {self.args.gradient_accumulation_steps}")
-            logger.info(f"  Total optimization steps = {max_steps}")
-            logger.info(f"  Number of trainable parameters = {count_parameters(self.model)[0]}")
+            logger.info("  Num examples = {}".format(num_examples))
+            logger.info("  Num Epochs = {}".format(num_train_epochs))
+            logger.info("  Instantaneous batch size per device = {}".format(self.args.per_device_train_batch_size))
+            logger.info("  Total train batch size (w. parallel, buffer, distributed & accumulation) = {}".format(
+                total_train_batch_size
+            ))
+            logger.info("  Gradient Accumulation steps = {}".format(self.args.gradient_accumulation_steps))
+            logger.info("  Num optimization epochs per batch = {}".format(self.finetuning_args.ppo_epochs))
+            logger.info("  Total training steps = {}".format(max_steps))
+            logger.info("  Number of trainable parameters = {}".format(count_parameters(self.model)[0]))

        unwrapped_model: "AutoModelForCausalLMWithValueHead" = self.accelerator.unwrap_model(self.model)
        dataiter = iter(self.dataloader)
--- a/src/llmtuner/train/ppo/workflow.py
+++ b/src/llmtuner/train/ppo/workflow.py
@@ -39,13 +39,14 @@ def run_ppo(
    reward_model = create_reward_model(model, model_args, finetuning_args)

    # Create ppo config
+    backward_batch_size = training_args.per_device_train_batch_size * training_args.gradient_accumulation_steps
    ppo_config = PPOConfig(
        model_name=model_args.model_name_or_path,
        learning_rate=training_args.learning_rate,
        mini_batch_size=training_args.per_device_train_batch_size,
-        batch_size=training_args.per_device_train_batch_size * training_args.gradient_accumulation_steps,
+        batch_size=backward_batch_size * finetuning_args.ppo_buffer_size,
        gradient_accumulation_steps=training_args.gradient_accumulation_steps,
-        ppo_epochs=1,
+        ppo_epochs=finetuning_args.ppo_epochs,
        max_grad_norm=training_args.max_grad_norm,
        seed=training_args.seed,
        optimize_device_cache=True,
@@ -62,9 +63,7 @@ def run_ppo(
    if training_args.max_steps > 0:
        num_training_steps = training_args.max_steps
    else:
-        total_train_batch_size = (
-            training_args.per_device_train_batch_size * training_args.gradient_accumulation_steps * training_args.world_size
-        )
+        total_train_batch_size = backward_batch_size * finetuning_args.ppo_buffer_size * training_args.world_size
        num_training_steps = training_args.num_train_epochs * math.ceil(len(dataset) / total_train_batch_size)

    lr_scheduler = get_scheduler(
@@ -94,7 +93,7 @@ def run_ppo(

    # Training
    if training_args.do_train:
-        ppo_trainer.ppo_train()
+        ppo_trainer.ppo_train(resume_from_checkpoint=training_args.resume_from_checkpoint)
        ppo_trainer.save_model()
        ppo_trainer.save_state() # must be called after save_model to have a folder
        if ppo_trainer.is_world_process_zero() and finetuning_args.plot_loss:
--- a/src/llmtuner/train/pt/workflow.py
+++ b/src/llmtuner/train/pt/workflow.py
@@ -6,7 +6,8 @@ from transformers import DataCollatorForLanguageModeling, Trainer

 from llmtuner.data import get_dataset, preprocess_dataset, split_dataset
 from llmtuner.extras.ploting import plot_loss
-from llmtuner.model import generate_model_card, load_model_and_tokenizer
+from llmtuner.model import load_model_and_tokenizer
+from llmtuner.train.utils import create_modelcard_and_push

 if TYPE_CHECKING:
    from transformers import Seq2SeqTrainingArguments, TrainerCallback
@@ -58,8 +59,4 @@ def run_pt(
        trainer.save_metrics("eval", metrics)

    # Create model card
-    if training_args.do_train:
-        if training_args.push_to_hub:
-            trainer.push_to_hub(**generate_model_card(model_args, data_args, finetuning_args))
-        else:
-            trainer.create_model_card(**generate_model_card(model_args, data_args, finetuning_args))
+    create_modelcard_and_push(trainer, model_args, data_args, training_args, finetuning_args)
--- a/src/llmtuner/train/rm/workflow.py
+++ b/src/llmtuner/train/rm/workflow.py
@@ -6,10 +6,11 @@ from transformers import Seq2SeqTrainingArguments
 from llmtuner.data import get_dataset, preprocess_dataset, split_dataset
 from llmtuner.extras.callbacks import SavePeftModelCallback
 from llmtuner.extras.ploting import plot_loss
-from llmtuner.model import generate_model_card, load_model_and_tokenizer
+from llmtuner.model import load_model_and_tokenizer
 from llmtuner.train.rm.collator import PairwiseDataCollatorWithPadding
 from llmtuner.train.rm.metric import compute_accuracy
 from llmtuner.train.rm.trainer import PairwiseTrainer
+from llmtuner.train.utils import create_modelcard_and_push

 if TYPE_CHECKING:
    from transformers import TrainerCallback
@@ -46,7 +47,7 @@ def run_rm(

    # Training
    if training_args.do_train:
-        train_result = trainer.train()
+        train_result = trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
        trainer.save_model()
        trainer.log_metrics("train", train_result.metrics)
        trainer.save_metrics("train", train_result.metrics)
@@ -68,8 +69,4 @@ def run_rm(
        trainer.save_predictions(predict_results)

    # Create model card
-    if training_args.do_train:
-        if training_args.push_to_hub:
-            trainer.push_to_hub(**generate_model_card(model_args, data_args, finetuning_args))
-        else:
-            trainer.create_model_card(**generate_model_card(model_args, data_args, finetuning_args))
+    create_modelcard_and_push(trainer, model_args, data_args, training_args, finetuning_args)
--- a/src/llmtuner/train/sft/trainer.py
+++ b/src/llmtuner/train/sft/trainer.py
@@ -39,10 +39,10 @@ class CustomSeq2SeqTrainer(Seq2SeqTrainer):
            prompt_len, label_len = inputs["input_ids"].size(-1), inputs["labels"].size(-1)
            if prompt_len > label_len:
                inputs["labels"] = self._pad_tensors_to_target_len(inputs["labels"], inputs["input_ids"])
-            if label_len > prompt_len:
-                inputs["labels"] = inputs["labels"][:, :prompt_len] # truncate the labels instead of padding the inputs
+            if label_len > prompt_len: # truncate the labels instead of padding the inputs (llama2 fp16 compatibility)
+                inputs["labels"] = inputs["labels"][:, :prompt_len]

-        loss, generated_tokens, _ = super().prediction_step(
+        loss, generated_tokens, _ = super().prediction_step( # ignore the returned labels (may be truncated)
            model, inputs, prediction_loss_only=prediction_loss_only, ignore_keys=ignore_keys
        )
        if generated_tokens is not None and self.args.predict_with_generate:
@@ -79,14 +79,19 @@ class CustomSeq2SeqTrainer(Seq2SeqTrainer):
        output_prediction_file = os.path.join(self.args.output_dir, "generated_predictions.jsonl")
        logger.info(f"Saving prediction results to {output_prediction_file}")

-        preds = np.where(predict_results.predictions != IGNORE_INDEX, predict_results.predictions, self.tokenizer.pad_token_id)
        labels = np.where(predict_results.label_ids != IGNORE_INDEX, predict_results.label_ids, self.tokenizer.pad_token_id)
+        preds = np.where(predict_results.predictions != IGNORE_INDEX, predict_results.predictions, self.tokenizer.pad_token_id)

+        for i in range(len(preds)):
+            pad_len = np.nonzero(preds[i] != self.tokenizer.pad_token_id)[0]
+            if len(pad_len):
+                preds[i] = np.concatenate((preds[i][pad_len[0]:], preds[i][:pad_len[0]]), axis=-1) # move pad token to last
+
+        decoded_labels = self.tokenizer.batch_decode(labels, skip_special_tokens=True, clean_up_tokenization_spaces=False)
        decoded_preds = self.tokenizer.batch_decode(preds, skip_special_tokens=True, clean_up_tokenization_spaces=True)
-        decoded_labels = self.tokenizer.batch_decode(labels, skip_special_tokens=True, clean_up_tokenization_spaces=True)

        with open(output_prediction_file, "w", encoding="utf-8") as writer:
            res: List[str] = []
-            for pred, label in zip(decoded_preds, decoded_labels):
+            for label, pred in zip(decoded_labels, decoded_preds):
                res.append(json.dumps({"label": label, "predict": pred}, ensure_ascii=False))
            writer.write("\n".join(res))
--- a/src/llmtuner/train/sft/workflow.py
+++ b/src/llmtuner/train/sft/workflow.py
@@ -7,9 +7,10 @@ from llmtuner.data import get_dataset, preprocess_dataset, split_dataset
 from llmtuner.extras.constants import IGNORE_INDEX
 from llmtuner.extras.misc import get_logits_processor
 from llmtuner.extras.ploting import plot_loss
-from llmtuner.model import generate_model_card, load_model_and_tokenizer
+from llmtuner.model import load_model_and_tokenizer
 from llmtuner.train.sft.metric import ComputeMetrics
 from llmtuner.train.sft.trainer import CustomSeq2SeqTrainer
+from llmtuner.train.utils import create_modelcard_and_push

 if TYPE_CHECKING:
    from transformers import TrainerCallback
@@ -90,8 +91,4 @@ def run_sft(
        trainer.save_predictions(predict_results)

    # Create model card
-    if training_args.do_train:
-        if training_args.push_to_hub:
-            trainer.push_to_hub(**generate_model_card(model_args, data_args, finetuning_args))
-        else:
-            trainer.create_model_card(**generate_model_card(model_args, data_args, finetuning_args))
+    create_modelcard_and_push(trainer, model_args, data_args, training_args, finetuning_args)
--- a/src/llmtuner/train/tuner.py
+++ b/src/llmtuner/train/tuner.py
@@ -37,8 +37,13 @@ def run_exp(args: Optional[Dict[str, Any]] = None, callbacks: Optional[List["Tra
 def export_model(args: Optional[Dict[str, Any]] = None, max_shard_size: Optional[str] = "10GB"):
    model_args, _, finetuning_args, _ = get_infer_args(args)
    model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args)
+
+    if getattr(model, "quantization_method", None) == "gptq":
+        raise ValueError("Cannot export a GPTQ quantized model.")
+
    model.config.use_cache = True
    model.save_pretrained(finetuning_args.export_dir, max_shard_size=max_shard_size)
+
    try:
        tokenizer.padding_side = "left" # restore padding side
        tokenizer.init_kwargs["padding_side"] = "left"
--- a/src/llmtuner/train/utils.py
+++ b/src/llmtuner/train/utils.py
@@ -3,16 +3,35 @@ from typing import TYPE_CHECKING, Literal, Union

 from llmtuner.extras.logging import get_logger
 from llmtuner.hparams import ModelArguments, FinetuningArguments
-from llmtuner.model import load_model_and_tokenizer, load_valuehead_params
+from llmtuner.model import get_modelcard_args, load_model_and_tokenizer, load_valuehead_params

 if TYPE_CHECKING:
+    from transformers import Seq2SeqTrainingArguments, Trainer
    from transformers.modeling_utils import PreTrainedModel
    from trl import AutoModelForCausalLMWithValueHead
+    from llmtuner.hparams import DataArguments


 logger = get_logger(__name__)


+def create_modelcard_and_push(
+    trainer: "Trainer",
+    model_args: "ModelArguments",
+    data_args: "DataArguments",
+    training_args: "Seq2SeqTrainingArguments",
+    finetuning_args: "FinetuningArguments"
+) -> None:
+    if training_args.do_train:
+        if training_args.push_to_hub:
+            trainer.push_to_hub(**get_modelcard_args(model_args, data_args, finetuning_args))
+            return
+        try:
+            trainer.create_model_card(**get_modelcard_args(model_args, data_args, finetuning_args))
+        except Exception as err:
+            logger.warning("Failed to create model card: {}".format(str(err)))
+
+
 def create_ref_model(
    model_args: "ModelArguments",
    finetuning_args: "FinetuningArguments",
--- a/src/llmtuner/webui/chatter.py
+++ b/src/llmtuner/webui/chatter.py
@@ -29,8 +29,17 @@ class WebChatModel(ChatModel):
        if not lazy_init: # read arguments from command line
            super().__init__()

-        if demo_mode: # load openchat 3.5 by default
-            super().__init__(dict(model_name_or_path="openchat/openchat_3.5", template="openchat"))
+        if demo_mode: # load demo_config.json if exists
+            import json
+            try:
+                with open("demo_config.json", "r", encoding="utf-8") as f:
+                    args = json.load(f)
+                assert args.get("model_name_or_path", None) and args.get("template", None)
+                super().__init__(args)
+            except AssertionError:
+                print("Please provided model name and template in `demo_config.json`.")
+            except:
+                print("Cannot find `demo_config.json` at current directory.")

    @property
    def loaded(self) -> bool:
--- a/src/llmtuner/webui/engine.py
+++ b/src/llmtuner/webui/engine.py
@@ -13,6 +13,7 @@ from llmtuner.webui.utils import get_time
 class Engine:

    def __init__(self, demo_mode: Optional[bool] = False, pure_chat: Optional[bool] = False) -> None:
+        self.demo_mode = demo_mode
        self.pure_chat = pure_chat
        self.manager = Manager()
        self.runner = Runner(self.manager, demo_mode=demo_mode)
@@ -22,7 +23,7 @@ class Engine:
        return {self.manager.get_elem_by_name(k): gr.update(**v) for k, v in resume_dict.items()}

    def resume(self) -> Generator[Dict[Component, Dict[str, Any]], None, None]:
-        user_config = load_config()
+        user_config = load_config() if not self.demo_mode else {}
        lang = user_config.get("lang", None) or "en"

        init_dict = {
Author	SHA1	Message	Date
hiyouga	7f54008d3c	update readme Former-commit-id: 561481a8008fde5a3273558460193864a09866ed	2023-11-21 13:15:46 +08:00
hiyouga	5f5959bc33	set version Former-commit-id: 6b47ad74c7b3099f9b5087c73db4aee42c451297	2023-11-20 22:57:44 +08:00
hiyouga	0105cd48f2	support GPTQ tuning #729 #1481 #1545 , fix chatglm template #1453 #1480 #1569 Former-commit-id: fdccc6cc9b68890199e9250cabdb996ff2f853b9	2023-11-20 22:52:11 +08:00
hiyouga	28258aecd2	update ppo trainer Former-commit-id: caa525a5c6f228b9ad71387d1fe4f1c2ffa2479e	2023-11-20 21:39:15 +08:00
hoshi-hiyouga	e585950c54	Merge pull request #1553 from hannlp/hans Change the default argument settings for PPO training Former-commit-id: 1b64678fa4979485f67c3bb1420dfdff6fcbc6e7	2023-11-20 20:32:55 +08:00
hiyouga	bcd661afa6	fix value head model resuming Former-commit-id: ccf0b65d886c09c7c49977c43b0544fe1bfcc258	2023-11-20 19:01:37 +08:00
hiyouga	adf2730d1d	fix #1567 Former-commit-id: 8c01ffe8d277d49a413571e0669f460c8d0802bf	2023-11-20 18:46:36 +08:00
hiyouga	ba2be6371d	better data streaming Former-commit-id: 65ac8e84fd6f22255c587b20382fdf5d8131d015	2023-11-19 23:32:47 +08:00
hiyouga	d2ff09a404	fix model card network issue Former-commit-id: 36155cd1893bea036f15c648c06b0047c02dfb4f	2023-11-19 23:03:19 +08:00
hiyouga	9f364d3880	fix Mistral template https://github.com/lm-sys/FastChat/pull/2547 Former-commit-id: d426ecdf6e95402fc36893f7e4f17f881e1b957b	2023-11-19 16:29:30 +08:00
hiyouga	cfad41b901	fix #1263 Former-commit-id: faff5d32621f187ebd3124d7ade04e3fa437c53e	2023-11-19 16:05:18 +08:00
hiyouga	6889f044fb	fix #1558 Former-commit-id: 263b2b24c8a649b51fa5ae768a24e67def8e0e96	2023-11-19 14:15:47 +08:00
hiyouga	3d1ee27ccd	fix evaluator and cached_file in 4.31.0 Former-commit-id: 970897da402f604220d45084d492de4dab809ba4	2023-11-18 19:39:23 +08:00
hiyouga	775ce62950	update benchmark Former-commit-id: 1cd2ae910e3ffca92978772d000de6fde2f6bb13	2023-11-18 11:30:01 +08:00
hiyouga	821a6f2fa6	update readme Former-commit-id: a4d86a4bea1cce2219a54def9dfd3fd732d48e72	2023-11-18 11:15:56 +08:00
hiyouga	5197fb2fad	add benchmark Former-commit-id: 85a09cb649be740a47359371499d821ee0d5c81e	2023-11-18 11:09:52 +08:00
hiyouga	92abe91d22	update dataset Former-commit-id: a310b22b446118d90dd73906847ed3d01a574b50	2023-11-17 23:19:12 +08:00
hiyouga	a7bf0b85d7	fix quantization Former-commit-id: 8268aefe8fba268065e24ffe159a9c49f7c6f3a5	2023-11-17 22:21:29 +08:00
hiyouga	5ce5ea84a9	fix #1550 Former-commit-id: c12acd21a5a500892ed739c79327ccd39fddad5b	2023-11-17 17:23:13 +08:00
Yuchen Han	992be39f90	Update README_zh.md Former-commit-id: 3e8a17c92d700bcafbe6559ea689dc4c0ad0481a	2023-11-17 00:18:07 -08:00
Yuchen Han	cab80a3c56	Update README.md Former-commit-id: c1532dc6fe5d5b427011bd5509a2bc44ee16d951	2023-11-17 00:17:36 -08:00
Yuchen Han	6af7107938	Update workflow.py Former-commit-id: f70b7ffe6442217a222e0ef797c407f259a13886	2023-11-17 00:16:27 -08:00
Yuchen Han	bcd31cf245	Update finetuning_args.py Former-commit-id: 30e3430553f1f7e09cd57ef2c9843b549746c618	2023-11-17 00:15:51 -08:00
hiyouga	85c4ccfef9	fix packages Former-commit-id: c93175d18ad9a4b7b61629153acabf8d0c978dfc	2023-11-17 16:11:48 +08:00
hoshi-hiyouga	dc0f81aabc	Merge #1544 from Outsider565/main, fix #1548 Fix: Change rouge-chinese package name to rouge_chinese Former-commit-id: c24da51cb5d3f78d54dcbfb31b565fcac4783a76	2023-11-17 16:09:42 +08:00
Shaowen Wang	07f934566a	Fix: Change rouge-chinese package name to rouge_chinese To reproduce: python: importlib.util.find_spec('rouge-chinese') -> None importlib.util.find_spec('rouge_chinese') -> ModuleSpec(name='rouge_chinese'...) from rouge_chinese import Rouge print(Rouge.__module__) -> rouge_chinese Former-commit-id: a78b11d944b6cb7dbe2a1d8a24d240e196aa530a	2023-11-16 20:12:35 -06:00
hiyouga	77cb18e9e3	fix chatglm template Former-commit-id: 6a4b79c2e0610a17012bf3e72a2b5e8bac060092	2023-11-16 22:54:15 +08:00
hiyouga	fccaecf730	Update bug-report.yml Former-commit-id: 92ed2297c78d016113fa7f90cedc0933a0bb2be0	2023-11-16 19:37:35 +08:00
hiyouga	53cdfe8f73	add issue template Former-commit-id: 4ca01a6b051043593541403d74e4d464b70e0e4b	2023-11-16 19:35:30 +08:00
hoshi-hiyouga	ea03523c6a	Update issue templates Former-commit-id: f967abcfcd052b65745f20e2c760ca45c412b66a	2023-11-16 18:56:30 +08:00
hiyouga	caf3cbf8d7	fix web ui demo Former-commit-id: e566a68a27872f730b111078977048755ec74a40	2023-11-16 18:41:55 +08:00
hiyouga	da411066c9	fix web ui demo Former-commit-id: 6fead193fe44fec74c2262d8653ed2f6006fac36	2023-11-16 17:12:23 +08:00