-
I have ran the script of finetune.py on my device, which has two V100 16G gpus, but encounter the problem of RuntimeError: expected scalar type Half but found Float. Does anyone meet the similar pro…
-
import logging
import os
import json
import torch
from datasets import load_from_disk
from transformers import TrainingArguments
from trl import SFTTrainer
from unsloth import FastLanguageModel…
-
### Your current environment
Collecting environment information.
PyTorch version: 2.3.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
0S: Cent0S Li…
-
能否基于之前的checkpoint继续训练？每次都需要重新开始会造成较多的时间浪费。
-
I would like to know how to use the trained model. It generates a checkpoint 30 folder, adapter_ Config.json and adapter_ model.bin。 How should I use Lora's finely tuned model? Can anyone help me?
…
-
Hello,
I have encountered a "division by zero" error while attempting to run `generator.py` on my Windows machine. I have made the necessary [modifications to `bitsandbytes`](https://github.com/oob…
-
Hello,
I'm currently working with the `transformers` library to train a model on causal language modeling tasks using the `MambaForCausalLM` class. However, I've noticed that the typical approach t…
-
-
### Describe the bug
Can not use multiple controlnets, https://huggingface.co/docs/diffusers/main/en/api/pipelines/controlnet_hunyuandit. According to the docs above, it seems that I just need to u…
-
When I load the model as following, throw the error: Cannot merge LORA layers when the model is loaded in 8-bit mode
How can I load model with 4bit when inferencing?
`
model_path = 'decapoda-resea…