-
Is it possible to do the fine tuning quantizing the models and using qlora?
-
### Feature request
In the quantization procedure for qlora, there is the 'nf'4 storage datatype and the compute datatype (in the paper bfloat16 which is the original)(please refer to the image). The…
-
(qloravenv) C:\deepdream-test\llm_qlora-main>python train.py C:\deepdream-test\llm_qlora-main\configs\mistralaiMistral-7B-v0.1.yaml
Load base model
Traceback (most recent call last):
File "C:\dee…
-
Tried fine-tuning the [InstructCodeT5+](https://huggingface.co/Salesforce/instructcodet5p-16b) model using QLoRA and the loss is stuck at a particular value. Code for the experiment:
```
import pand…
-
### 是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?
- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
### 该问题是否在FAQ中有解答? | Is there an existing ans…
-
使用qlora微调的时候,由于微调的数据过长显存溢出,能设置多卡qlora微调吗
-
ValueError: FP16 Mixed precision training with AMP or APEX (`--fp16`) and FP16 half precision evaluation (`--fp16_full_eval`) can only be used on CUDA devices.
请问这个错误怎么解决?
-
**base-model: Weyaxi/Dolphin2.1-OpenOrca-7B**
**Scenario:**
- followed the following guidelines - https://github.com/intel-analytics/ipex-llm/tree/main/python/llm/example/GPU/LLM-Finetuning/QLoRA…
-
For workloads such as QLoRA, we can save and upload (or use existing ones) pre-quantized model weights, which would have a couple of benefits:
- Allow users to save disk space by only working with 4-…
-
llama2_7b_qlora_alpaca_enzh_e3.py作为模板,qlora微调gsm8k,修改PROMPT_TEMPLATE.llama2_chat为PROMPT_TEMPLATE.llama3_chat,acc从62下降到28,可能是什么原因导致的?