-
你好，
我的环境是13th Gen Intel(R) Core(TM) i9-13900HX 2.20 GHz，内存64G，显卡是NVIDIA GeForce RTX 4090 16G显存。
我有两个问题：
1、直接运行模型python examples/generate_finetune_web.py --base_model ./model/knowlm-13b-base-v1.0
…
-
I have 8 NVIDIA GeForce RTX 2080 Ti. I have used following command to run the project:
```
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python examples/generate_lora.py --base_model /data2/user/LLM/knowlm-1…
-
您好，经过测试，device="cpu"，python examples/generate_finetune_web.py --base_model ./model/knowlm-13b-base-v1.0中产生的RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'问题解决了。
但是如果在generate…
-
**Describe the bug**
> A clear and concise description of what the bug is.
用example/llm/InstructKGC/src/inference.py进行NER。模型用的是knowlm-13b-ie。类型为"老人旅客"和"孕妇旅客"。
测试数据如下：
{"id": "1e073138ed48eeb6f97…
-
在执行这条命令时：python examples/generate_finetune.py --base_model zjunlp/knowlm-13b-base-v1.0
发现下载超时了，该如何解决
[错误信息.txt](https://github.com/zjunlp/KnowLM/files/12882269/default.txt)
-
Hello, thank you for your work!
I am really interested in this repo, but I run into a issue which I don't think can be addressed without help.
I ran the progress in the official knowLM container:
…
-
**Describe the question**
Getting RecursionError when trying to make inference with
`CUDA_VISIBLE_DEVICES=1,2 python src/inference.py \
--model_name_or_path ...xxx/model_weights/knowlm-13b-zhi…
-
代码里启动lora的web，把lora的weight加载去掉了？意思是KnowLM-13B-ZhiXi和KnowLM-13B-IE都是全参数微调的吗？但是我看后面的训练细节里写，抽取的ner/re/ee都是用的lora训练的，有点懵。全参数微调的有训练脚本吗？
-
CUDA SETUP: Required library version not found: libsbitsandbytes_cpu.so. Maybe you need to compile it from source?
CUDA SETUP: Defaulting to libbitsandbytes_cpu.so...
/opt/conda/envs/zhixi/lib/pytho…
-
when I use "python examples/generate_lora_web.py --base_model ./model/knowlm-13b-ie", it would create the error like this:
(knowlm) G:\KnowLM-main>python examples/generate_lora_web.py --base_model ./…