-
Traceback (most recent call last):
File "/root/miniconda/envs/thj/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/root/miniconda/…
-
`
import torch
import torch.nn as nn
from peft import get_peft_model, LoraConfig, PeftModel
from accelerate import Accelerator
class Encoder(nn.Module):
def __init__(self):
supe…
-
Hello
I am running in the following machine.
CPU: 12th Gen Intel(R) Core(TM) i7-12700
RAM: 32GB, speed: 4400MT/s
NVIDIA RTX A2000 12GB
model is:
llama-2-7b-chat.Q6_K.gguf
And it takes a…
-
Since my training environment could not connect to the internet, I download the model and dataset and save them in the local disk.
The arguments:
**model path**: ModelArguments(base_model_revision=N…
-
### Please check that this issue hasn't been reported before.
- [X] I searched previous [Bug Reports](https://github.com/axolotl-ai-cloud/axolotl/labels/bug) didn't find any similar reports.
### Exp…
-
I always get a weird output after the training when generating text (see screenshots)
The following tags are appended to the output 95% of the time:
'### further instruction:'
'### input:'
'### …
-
-
### 🚀 The feature, motivation and pitch
Sparse Causal Flash Attention as implmented [here](https://github.com/epfml/dynamic-sparse-flash-attention) and described in [this paper](https://arxiv.org/abs…
-
Environment:
```
git clone https://github.com/tloen/alpaca-lora.git
cd alpaca-lora
git clone https://huggingface.co/tloen/alpaca-lora-7b
```
Stacktrace:
```
(alpaca-lora) root@host:~/alpac…
-
**Describe the bug**
4xA100 gpu fine-tuning llama-3.1-8b-instruct (also tried llama2-13b-ms, same error), cli
```
CUDA_VISIBLE_DEVICES=0,1,2,3 \
NPROC_PER_NODE=4 \
LOCAL_WORLD_SIZE=4 \
swift…