LongWriter

LongWriter copied to clipboard

请问step_parallel的prompt和代码有开源吗？

1

### System Info / 系統信息 。 ### Who can help? / 谁可以帮助到您？ 。 ### Information / 问题信息 - [X] The official example scripts / 官方的示例脚本 - [X] My own modified...

mrpen2

[rank4]: Input should be a valid integer, got a number with a fractional part [type=int_from_float, input_value=15099494.4, input_type=float]

13

我使用官方提供的脚本和数据集先后运行了python pre_tokenize_glm4.py python sort_and_group.py --group_size 8 --train_file /home/hnjj/diskdata/yuanshi/media/szf/llm/glm_longwrite/LongWriter/train/datasets 得到了attention_masks_pack.json ，inputs_pack.npy等文件 运行训练脚本 ./glm4_longwriter.sh 时，遇到与 DeepSpeedZeroConfig 配置相关的 ValidationError。错误是由于 stage3_prefetch_bucket_size 的输入类型无效，期望为整数但接收到浮点数。 训练日志： [2024-08-26 09:58:48,719] [INFO] [comm.py:683:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl...

sunzhufeng12345

Will this work well if I were to give it input sources and ask it to generate an article/report from that?

2

### Feature request / 功能建议 Hi Thanks for a great model. I was wondering if this fits my usecase. Essentially I'm looking for grounded generation. For eg. I give it...

regstuff

是否在ollama中测试过速度？

1

在ollama中导入hugging face上4bit量化后的gguf格式模型，在openwebui中提问，输出速度很慢。 ollama主机4060ti 16g型号的显卡显存占用才8G，显卡核心频率经常在210，很少到最大频率，7950x的CPU占用率50％。

allenxml

eos_indices = input_ids.argmin(dim=1) - 1

2

script/main.py中 class DataCollatorForLMDataset(object): def __call__(self, instances: Sequence[Dict]) -> Dict[str, torch.Tensor]: input_ids, labels = tuple([instance[key].unsqueeze(0) for instance in instances] for key in ("input_ids", "labels")) input_ids = torch.cat(input_ids, dim=0) labels = torch.cat(labels,...

xpdd123

这个需要多大得显存可以跑起来RTX4090 24G可以吗

9

### System Info / 系統信息 这个需要多大得显存可以跑起来RTX4090 24G可以吗 ### Who can help? / 谁可以帮助到您？ _No response_ ### Information / 问题信息 - [ ] The official example scripts / 官方的示例脚本 - [...

anstonjie

Error making gguf: KeyError: '<|user|>'

7

### System Info / 系統信息 transformers: 4.44.0 llama.cpp: latest Hi, when I try to make a gguf I get this error: > Traceback (most recent call last): File "/home/david/llm/llama.cpp/convert_hf_to_gguf.py", line...

arch-btw

点击Submit，页面显示错误，控制台显示AttributeError: 'PrelrainedlokenizerFast' object has no attribute 'build_chat_input'

4

### System Info / 系統信息 CUDA ：11.1 transformers：4.44.0 Python：3.10.0 操作系统：Windows10 64 ### Who can help? / 谁可以帮助到您？ _No response_ ### Information / 问题信息 - [X] The official example scripts /...

1105135335

History of iran

Sinam137

Getting stuck

3

Often it gets stuck here. Like this:  However, I'm running this from a gguf via GPT4ALL in Blender, so there might be multiple things causing this. I just wonder,...

tin2tin