Comments (2)
可以去仔细看下代码,我的理解是如果create_new_adapter为True,则会在代码中将adapter_name_or_path与基模先merge起来,然后再添加新的adapter进行训练,反之create_new_adapter为False,则是在adapter_name_or_path基础上进一步训练,最后保存优化后的adapter,两种方法的本质效果是一致的,但第一种会产生两个adapter参数,第二种就只有一个adapter参数,不知道我的理解是否正确 : )
from llama-factory.
如果采用第一种方式进行训练的话,最后导出模型的话,是直接和原始的模型进行合并,还是和sft的模型进行合并
#!/bin/bash
DO NOT use quantized model or quantization_bit when merging lora weights
CUDA_VISIBLE_DEVICES=0 python ../../src/export_model.py
--model_name_or_path /mnt/data/legalexp/LLM_exp/MiniCPM/MiniCPM-2B-sft-bf16
--adapter_name_or_path ../../saves/LLaMA2-7B/lora/dpo
--template default
--finetuning_type lora
--export_dir ../../saves/minicpm_dpo
--export_size 2
--export_legacy_format False
from llama-factory.
Related Issues (20)
- Qwen2 7B SFT 无法启动训练 HOT 1
- 预训练 Running tokenizer on dataset 执行了两遍 HOT 1
- Qwen-1.5-14b-chat多卡推理时加载权重速度很慢 HOT 1
- 使用 qwen2 7b int8 在 webui 中 chat 时所有的回答都是乱码 HOT 7
- Lora方式对Qwen1.5-7B进行增量预训练,loss值下降幅度很小 HOT 1
- 使用llamafactory-cli api启动Qwen/Qwen2-7B-Instruct回答乱码 HOT 2
- [NPU] inference ZhipuAI/glm-4-9b-chat POST /v1/chat/completions ERROR: Exception in ASGI application HOT 1
- qwen2 awq 微调一直报错 auto-awq kernels没有安装 HOT 1
- 加载数据时,如果存在cache,debug用参数max_samples将失效 HOT 1
- How to get logit during prediction HOT 1
- Dockerfile is missing unsloth HOT 1
- webui界面导出的时候需要选择适配器,这个去哪选择呀 HOT 4
- Why can not set eval dataset in examples/lora_single_gpu/llama3_lora_sft.yaml ?? HOT 2
- RuntimeError: Cannot find valid samples, check `data/README.md` for the data format. HOT 3
- training is broken with vllm==0.5.0
- 执行llamafactory-cli webui报错 Exception in thread Thread-3 (_do_normal_analytics_request) HOT 2
- auto-awq kernels is needed to be installed to use .backward() #19 HOT 1
- Error in launch using a docker image HOT 1
- 支持glm-4-v-9b微调吗 HOT 1
- why not cast dtype in deepspeed zero3 ? HOT 6
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 llama-factory.