-
在sft.py 的
769行开始德循环内logger.warning(f"tokenization mismatch: {cur_len} vs. {total_len}. (ignored)") 这里
cur_len 一直为1
| WARNING | __main__:preprocess_function:813 - tokenization mismatch: 1 vs. 81.…
-
Hello everyone,
I would like to inquire as to why you have chosen Bloom-7b1 as your paper description. As far as I know, BigScience recommends using Bloomz variants, which can be found by following t…
-
RT
-
Does this program supports tensorboard? Could not find any logs of tensorbard.
-
I get following error while trying to fine tuning with p_tuning using FSDP with CPU offload and accelerate -
```
return forward_call(*args, **kwargs)
File "/home/datascience/conda/pytorch_2_v1…
-
Give OpenVoiceOS some sass with Persona!
Phrases not explicitly handled by other skills will be run by Persona, so nearly every interaction will have _some_ response. But be warned, OpenVoiceOS m…
-
While converting the [bloomz](https://huggingface.co/bigscience/bloomz-7b1l) model, I am getting the 'invalid syntax' error. Is conversion limited to only predefined model types?
If not, please provi…
-
I try to deepspeed local mode, download huggingface bigscience/bloomz-7b1-mt
set tensor_parallel=4 run success, but set tensor_parallel 5、6、7、8，it’s doesn't work
```
mii_configs = {
"dtype": "…
-
BELLE7b是对BLOOMZ-7B1-mt的优化，是通过train/finetune.py的方式吗，是否可以介绍一下
另外，我如果用bloom3b进行优化，通过finetune的方式可行吗 @xianghuisun
-
Not sure if we should consider this out of scope, but `bloomz.cpp` is a fork of `llama.cpp` that's capable of inference with the BLOOM family of models. The changes don't look very large, so there's r…