Comments (2)
加参数:--lora_target W_pack
from llama-factory.
百川的attention应该是把(Wq,Wk,Wv) concat成一个W_pack了
from llama-factory.
Related Issues (20)
- 自定义数据集加载报错 HOT 4
- How can I configure llama-factory to use multiple GPU cards? 2x amd radeon rx 7900 xtx HOT 1
- DPO阶段会将数据转换为 [prompt_ids, chosen_ids, rejected_ids], 在 traininer.train 的时候报错缺少 'input_ids'. HOT 1
- data/alpaca_data_zh_51k.json存在非标准的列名 HOT 1
- 支持自定义模型的接入及其多模态模型的训练吗? HOT 4
- 训练方法如何训练偏好数据集 HOT 1
- torch.distributed.DistBackendError: NCCL error in: /opt/pytorch/pytorch/torch/csrc/distributed/c10d/ProcessGroupNCCL.cpp:1727, unhandled system error (run with NCCL_DEBUG=INFO for details), NCCL version 2.19.
- question about labels HOT 1
- Does LLaMA-Factory support AMD graphic cards? HOT 7
- Qwen1.5-MOE-A2.7B训练问题 HOT 1
- LoftQ + Unsloth ? HOT 1
- webUI加载模型速度很慢怎么回事 HOT 1
- 可以适配 OIG dataset 以及全量微调pythia模型吗?
- oom when sft Qwen1.5-32B-Chat using deepspeed z3 offload + bs1
- 是否支持yuan2 HOT 2
- Warning 未检测到 CUDA 环境。 HOT 3
- Train with Nested rlhf datset format HOT 1
- evaluate eval HOT 3
- 导出sft后的的qwen-7b-chat模型,报错NotImplementedError:cannot copy out of meta tensor; no data! HOT 1
- 模型评估的方式不太适合完成的任务,应该怎么修改 HOT 3
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.