Comments (6)
Yes, you can download large models after installing git lfs, this will increase your download speed and download success, for example you can download the vicuna-13b model with this command
git clone https://huggingface.co/Tribbiani/vicuna-13b
,"Tribbiani/vicuna-13b" is the address of the model in the hf.
This is because your model file could not be found, the path to each model file may be different, you can try changing the index, e.g.
model_path = os.path.join(". /model", os.listdir("model")[0])
, I know this approach may not be very smart, we may introduce env later to manage model integration.This is because your model file could not be found, the path to each model file may be different, you can try changing the index, e.g.
model_path = os.path.join(". /model", os.listdir("model")[0])
, I know this approach may not be very smart, we may introduce env later to manage model integration.@zhanghy-sketchzh Thanks, how do we copy models into model directory
Do i have to download this from huggingface
https://huggingface.co/tiiuae/falcon-7b/blob/main/pytorch_model-00002-of-00002.bin and put bin files in model folder ? my model folder is empty
Yes, you can download large models after installing git lfs, this will increase your download speed and download success, for example you can download the vicuna-13b model with this command git clone https://huggingface.co/Tribbiani/vicuna-13b,"Tribbiani/vicuna-13b" is the address of the model in the hf.
from db-gpt-hub.
This is because your model file could not be found, the path to each model file may be different, you can try changing the index, e.g. model_path = os.path.join(". /model", os.listdir("model")[0])
, I know this approach may not be very smart, we may introduce env later to manage model integration.
from db-gpt-hub.
This is because your model file could not be found, the path to each model file may be different, you can try changing the index, e.g.
model_path = os.path.join(". /model", os.listdir("model")[0])
, I know this approach may not be very smart, we may introduce env later to manage model integration.
This is because your model file could not be found, the path to each model file may be different, you can try changing the index, e.g.
model_path = os.path.join(". /model", os.listdir("model")[0])
, I know this approach may not be very smart, we may introduce env later to manage model integration.
@zhanghy-sketchzh Thanks, how do we copy models into model directory
Do i have to download this from huggingface
https://huggingface.co/tiiuae/falcon-7b/blob/main/pytorch_model-00002-of-00002.bin and put bin files in model folder ? my model folder is empty
from db-gpt-hub.
Thanks I will try
from db-gpt-hub.
I got MemoryError @zhanghy-sketchzh and I am running it on CPU, I don't have GPU in my machine.
laptop RAM is 8 GB
Will this work on google colab ?
bin /home/tushar/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so
/home/tushar/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/bitsandbytes/cextension.py:34: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
warn("The installed version of bitsandbytes was compiled without GPU support. "
/home/tushar/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined symbol: cadam32bit_grad_fp32
CUDA SETUP: Loading binary /home/tushar/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so...
loading base model ./model/pytorch_model-00001-of-00002.bin...
Traceback (most recent call last):
File "/home/tushar/TextSQL/DB-GPT-Hub/src/train/train_qlora.py", line 831, in <module>
train()
File "/home/tushar/TextSQL/DB-GPT-Hub/src/train/train_qlora.py", line 667, in train
model = get_accelerate_model(args, checkpoint_dir)
File "/home/tushar/TextSQL/DB-GPT-Hub/src/train/train_qlora.py", line 276, in get_accelerate_model
model = AutoModelForCausalLM.from_pretrained(
File "/home/tushar/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 461, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/home/tushar/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 986, in from_pretrained
config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
File "/home/tushar/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/transformers/configuration_utils.py", line 617, in get_config_dict
config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
File "/home/tushar/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/transformers/configuration_utils.py", line 702, in _get_config_dict
config_dict = cls._dict_from_json_file(resolved_config_file)
File "/home/tushar/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/transformers/configuration_utils.py", line 793, in _dict_from_json_file
text = reader.read()
MemoryError
./scripts/spider_qlora_finetune.sh: 11: --source_max_len: not found
from db-gpt-hub.
This project requires a GPU and can work on google colab
from db-gpt-hub.
Related Issues (20)
- 多轮对话的训练数据格式 HOT 1
- 有微调好的大模型吗? HOT 3
- how to configure azure llm and embedding model ? HOT 1
- Text2SQL评估指标EX和TS HOT 1
- 请问怎么用bird数据集微调codellama呢? HOT 2
- 请问推理的时候为什么不使用批量的方式呢? HOT 2
- Baseline execution accuracy metric error HOT 1
- 三张3090卡可以不开量化用lora在BIRD数据集上微调吗 HOT 3
- Bird数据集评估的时候要传入的predict_dev.json文件的格式是什么样的?
- 可以公开一下hugging face上的lora模块的微调参数吗 HOT 1
- CodeLlama SFT
- 模型训练完进行合并权重时,显示does not contain a LoRA weight HOT 1
- Prompt for CodeLlama model HOT 1
- 网页刷新后 每个会话的模型选择恢复到默认模型 无法模型选择记忆化 HOT 1
- predict_sft.sh 推理速度好慢
- RuntimeError: expected mat1 and mat2 to have the same dtype, but got: float != c10::Half HOT 2
- codellama70B probably needs how much memory to train the spwider dataset?
- 在windows server上可以安装么? HOT 1
- 麻烦更新一下微信群的二维码,谢谢~
- 请问怎么自定义数据集 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from db-gpt-hub.