Giters
THUDM
/
GLM
GLM (General Language Model)
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
3080
Watchers:
46
Issues:
190
Forks:
316
THUDM/GLM Issues
WudaoCorpus-Dialog
Closed
a year ago
Comments count
1
where I can check the source code of model.generate()
Closed
a year ago
Comments count
1
GLM-10B怎么使用模型并行
Updated
a year ago
Comments count
2
如何使用在huggingface下载的离线模型推理glm-10b-chinese?
Updated
a year ago
Comments count
2
使用ds_pretrain_nvidia.sh后模型生成异常
Closed
a year ago
Comments count
3
请问GLM-10B-Chinese的tokenizer是否支持添加自定义的token?如果支持的话大概的方式是什么?非常感谢!
Closed
a year ago
Why does the model occupy less GPU memory after quantization, but the inference speed is slower?
Updated
a year ago
Comments count
1
glm_10B_chinese在finetune的时候需要多久,目前已经六个小时还未结束,运行的命令是github上给出的bash scripts/generate_block.sh \ config_tasks/model_blocklm_10B_chinese.sh,且一直未有log输出 ,但gpu是有利用率的
Closed
a year ago
Comments count
3
1
Closed
a year ago
MPU module
Closed
a year ago
Comments count
2
For `GLM-10B-Chinese`, the fine-tuning loss barely decrease within each epoch and it only decreases when starting a new epoch.
Closed
a year ago
Comments count
3
生成结果“随机性固定”的问题
Closed
a year ago
Comments count
2
ImportError: cannot import name 'torch_required' from 'transformers.utils'
Closed
a year ago
Comments count
2
GLM-10B chinese and MP_SIZE= 2 for pretrain just stay in the function of get_train_val_test_data ?
Closed
a year ago
Comments count
3
generate empty sample
Closed
a year ago
运行scripts/generate_block.sh,在生成的过程中中断并报错
Closed
a year ago
Comments count
2
Questions about 10B-chinese
Closed
a year ago
Comments count
2
同一个句子中多个[MASK]无法同时预测
Closed
a year ago
Comments count
2
How to finetune for text generation?
Closed
a year ago
Comments count
10
AutoModelForMultipleChoice无法加载glm-large-chinese模型
Closed
a year ago
Comments count
2
Question about how to finetune 10b-chinese model for summarization task
Updated
a year ago
How are the escape characters '\n' or '\t' in data processed during pretraining or finetuing?
Closed
a year ago
Comments count
8
如何操作:glm-10b-chinese不做finetune直接加载pretrained model做inference
Closed
a year ago
Comments count
13
Bug of finetuning code? the attention mask of padding is not 0.
Closed
a year ago
Comments count
2
glm-10B-chinese是如何finetune的,运行的脚本文件是哪个
Closed
a year ago
Comments count
1
Deepspeed zero stage 3
Updated
a year ago
Comments count
3
如果用 AutoModelForSeq2SeqLM 的格式进行下游finetune 后 除了使用save_pretrained 方法进行储存外 还需要进行哪些操作 才能再次用 AutoModelForSeq2SeqLM.from_pretrained本地初始化?
Updated
a year ago
Comments count
1
4bit quantization of the 10b model
Updated
a year ago
Model Warmup for ICL
Closed
a year ago
Comments count
2
Can not reproduce SQuAD v1.1 result using GLM-Large
Closed
a year ago
Comments count
1
Why not release GLM-base-chinese?
Closed
a year ago
Train the glm-10B-chinese model using 4 V100 GPUs, with no error logs printed, and then exit
Closed
a year ago
Comments count
6
The pretraining corpus of GLM-Large-Chinese
Closed
a year ago
Comments count
1
Hello, below are some questions I encountered while learning code, I hope you can answer them when you have time, thank you.
Closed
a year ago
Comments count
1
Aboutlength
Closed
a year ago
How many cards do you need to fine-tune this model?
Closed
a year ago
In `GLM-10B-Chinese`, token id for `[gMASK]` and `[eop]` is the same. Is it a designed behavior?
Closed
a year ago
Comments count
1
Unrecognized configuration class
Closed
a year ago
Comments count
1
Which config is used to pretrain the released `GLM-10B-Chinese` model? is `ds_block_10B_chinese_longer.sh` or `ds_block_10B_chinese.sh`
Closed
a year ago
Comments count
1
Unable to use `AutoModelForSeq2SeqLM`
Closed
2 years ago
Comments count
3
convert pretrained pt to huggingface
Closed
2 years ago
Comments count
1
Accelerate the model inference of GLM-10B
Closed
a year ago
Comments count
2
Hardware requirements for GLM-chinese-10B
Updated
a year ago
Comments count
9
Information about those new released multi-task model
Closed
2 years ago
Comments count
1
自定义tokenizer
Closed
a year ago
Hardware requirements
Updated
2 years ago
模型权重加载问题
Closed
2 years ago
Comments count
2
run infer failed
Closed
2 years ago
Comments count
4
how to choose the finetuning script for question-answering task
Closed
2 years ago
Comments count
2
运行(bash scripts/generate_block.sh config_tasks/model_blocklm_10B_chinese.sh)代码时生成的文本与示例中的不一致
Closed
2 years ago
Comments count
2
Previous
Next