-
Hi @sayakpaul @osanseviero, here is the outline proposal for the blog we discussed. Let me know what you think!
1. How HuggingFace eco-system (transformers, diffusers, etc.) helps access state-of-t…
-
### Question
There is great potential in this piece of work as one of the few open-sourced multimodal LLMs out there. Recently, there have been a number of works leveraging on LLMs to exploit tools a…
-
https://speakerdeck.com/ksaito/llmniri-ben-yu-tekisutowoxue-xi-saseruyi-yi
-
Hi,
We're running a project in the CivicLab in Grenoble, France. The project is based on LLM and is building as opensource project.
We're trying to build, test, prototype and evaluate an assistant…
-
Hi Huggingface Nanotron team!
Can I request some tooling surrounding nanotron regarding how fast it is compared to other LM training frameworks e.g. FSDP, Deepspeed, and Megatron-LM? It would be gr…
-
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 2995886) of binary: /usr/bin/python3
@dl:~/llama$ CUDA_VISIBLE_DEVICES="5,6,7" torchrun --nproc_per_node…
-
### Feature request
I have been searching through a lot of websites and watching youtube videos on how to deploy opensource LLM models locally on a windows server and then it could be further exposed…
-
ttaop updated
3 months ago
-
Hi Turbo,
I am interested in doing some model self-merges. Currently, I do this with a script with huggingface models.
Basically, I calculate the mapping, eg to duplicate layer 3:
{1:1, 2:2,3:3…
-
效果特别好。想请教作者，如果训练数据不方便开源的话，能不能分享一下如何制作或者收集lora训练数据集的方法或者思路？
再次感谢作者