-
https://github.com/JL-er/RWKV-PEFT
-
您好，我在使用您提供的代码中/reproduce/utils.py中的merge_llama函数和/examples/merge.py，对用meta-math按照论文参数设置训练的llama2-7b进行merge后，模型总大小从原先的12G扩大到了20G，并且无论输入总输出大段空白，但对t5-base进行merge前后模型大小几乎相等，想问下这是正常的吗？图中是merge函数。
训练的命令：
…
-
Hello, thank you for providing this excellent model and repository. I encountered an issue while conducting my experiments with your codebase, and I’d appreciate your insights.
In my experiments, I…
-
### Feature request
Integrate merge-kit functionalities within the PEFT library to enable users to leverage the techniques provided in the library.
This could include additional merging techniques…
-
File "C:\Program Files\Python312\Lib\site-packages\torch\nn\modules\module.py", line 1333, in convert
raise NotImplementedError(
NotImplementedError: Cannot copy out of meta tensor; no data! Pl…
-
An error occurs when loading a model using a for loop as shown below.
What could be the problem?
```py
for peft_model_id in peft_model_ids:
print(peft_model_id)
model, tokenizer =…
-
## ❓ General Questions
Hello, I was wondering if mlc-llm supports converting Huggingface models trained with [PEFT](https://github.com/huggingface/peft). I did a quick search of documentation and i…
-
### System Info
```Shell
- `Accelerate` version: 0.34.2
- Platform: Linux-5.14.0-362.24.2.el9_3.x86_64-x86_64-Intel-R-_Xeon-R-_Silver_4216_CPU_@_2.10GHz-with-glibc2.37
- `accelerate` bash locati…
-
### System Info
- Python 3.10
- torch==2.4.1 and torch==2.5.1+cu121
- bitsandbytes==0.44.1
- llama-recipes 0.4.0.post1 and 0.4.0
### Reproduction
While running:
```bash
torchrun --nnodes…
-
基础模型：llama-7b-hf
我尝试将微调后的参数合并，但出现了错误
`Traceback (most recent call last):
File "/home/kww/test_model.py", line 24, in
merged_model = model.merge_and_unload(safe_merge=True)
File "/home/…