-
Context:
Environment: Google Colab (Pro Version using a V100) for training.
Tool: Utilizing Hugging Face AutoTrain for fine-tuning a language model.
Sequence of Events:
**Initial Training:**
…
-
Any plans to add a recipe for further pre-training on custom data with optional tokenizer vocab extension in the style of [chinese-llama](https://github.com/ymcui/Chinese-LLaMA-Alpaca/blob/main/README…
-
**Describe the bug**
I am trying to finetune Mistral Instruct V0.2 and I keep getting this error.
`TypeError: LoraConfig.__init__() got an unexpected keyword argument 'use_rslora`
`
**To Reproduc…
-
### What is the issue?
Moving from 0.3.6 to 0.3.7-rc5, Ollama no longer uses both GPUs for a single model when the model will not fit on one card. If I load two models, though, it will use the secon…
-
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
import torch
from PIL import Image
import requests
from modelscope import snapshot_download
from transformers impo…
-
### What happened?
The llama.cpp tokenizer for Phi-3 has odd behavior, where re-tokenizing the same text over and over keeps adding whitespaces to the first non-BOS token. This has several issues:
…
-
**Describe the bug**
Even after applying ZeRO3, model parameters are copied, not partitioned, across all the available GPUs
**To Reproduce**
When I run the below code with this command: `deepspee…
-
Thank you for the handy fine tuning guide but I am not able to get started.
I tried using the default settings as a POC but it ends up erroring out.
This is the output I get when using the sampl…
-
Hello,
I am testing out the SFT stage of the example on a `p3.16xlarge` machine. But it OOMs. Is there anything that I is missing from my configs?
Note: I commented out the data so that it pick…
-
### What is the issue?
Steam Deck GPU not supported (apperantly)
Logs:
> time=2024-03-19T11:24:28.162Z level=INFO source=images.go:806 msg="total blobs: 54"
> time=2024-03-19T11:24:28.420Z lev…