OKC0

Results 9 issues of OKC0

漏字问题严重?

what is the sft template? when i try to use this model, i dont know what is the sft template. please help me, thankyou

### Describe your problem 如何链接到本地部署的LLM? 如下。

question

### 提交前必须检查以下项目 - [X] 请确保使用的是仓库最新代码(git pull) - [X] 已阅读[项目文档](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3/wiki)和[FAQ章节](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3/wiki/常见问题)并且已在Issue中对问题进行了搜索,没有找到相似问题和解决方案。 - [X] 第三方插件问题:例如[llama.cpp](https://github.com/ggerganov/llama.cpp)、[text-generation-webui](https://github.com/oobabooga/text-generation-webui)等,建议优先去对应的项目中查找解决方案。 ### 问题类型 模型训练与精调 ### 基础模型 Llama-3-Chinese-8B(基座模型) ### 操作系统 None ### 详细描述问题 预训练base时的学习率多少?我在想参考下,设置sft学习率。谢谢 ### 依赖情况(代码类问题务必提供) ``` # 请在此处粘贴依赖情况(请粘贴在本代码块里) ```...

stale

UIEPredictor 中无batch 填充逻辑。会导致报错: File "/home/wangjiawei/baishen/UIE/uie_predictor.py", line 560, in _auto_joiner for i in range(len(short_results[v])): IndexError: list index out of range

Some weights of UIE were not initialized from the model checkpoint at uie_m_large_pytorch and are newly initialized: ['encoder.embeddings.token_type_embeddings.weight'] 加载uie_m_large_pytorch ,提示有部分权重无法加载

ground_truth_sqls=./bird/dev_gold db_path='./bird/database/' result_save_path='./bird/dev_result.bin' num_cpus=32 echo '''pre-compute dev results''' python3 -u ./bird/prestore_dev_result.py --ground_truth_sqls ${ground_truth_sqls} --db_path ${db_path} --num_cpus ${num_cpus} --result_save_path ${result_save_path}

![Image](https://github.com/user-attachments/assets/0cf0e936-c8a0-4071-b6b0-91dd2557efd2)