Comments (3)
ghscut
commented on May 22, 2024
补充: cli_demo参数换成https://github.com/ymcui/Chinese-LLaMA-Alpaca/blob/main/scripts/inference/inference_hf.py这里面参数后, 结果更离谱, 如下:
gen_kwargs = {
"input_ids": input_ids,
"do_sample": True,
"top_p": 0.9,
"temperature": 0.2,
"top_k":40,
"num_beams": 1,
"max_new_tokens": 400,
"repetition_penalty": 1.3,
"logits_processor": get_logits_processor(),
"streamer": streamer
}
from llama-factory.
hiyouga
commented on May 22, 2024
修改了template，重新试一下呢。
from llama-factory.
ghscut
commented on May 22, 2024
ok, 已经正常，感谢~
from llama-factory.
Related Issues (20)
- adding language
- How to estimate total steps and set proper
- [Feature Request] support for new peft model `pissa` HOT 1
- 在昇腾npu环境下运行报错 HOT 4
- llama3增量预训练冻结哪些层训练哪些层效果比较好？ HOT 1
- Question about --dpo_ftx Parameter Setting HOT 1
- 请教一下如何不使用任何模版加载数据？ HOT 2
- api部署，method not allowed问题 HOT 1
- Fail to run mixture-of-depths sft official example script HOT 4
- orpo训练较慢 HOT 3
- SFT微调完成导出模型的API推理问题 HOT 2
- ascend 910b,chatglm2做全量微调报错
- 请教全量微调时deepspeed保存事项 HOT 3
- bash: llamafactory-cli: command not found HOT 1
- Sprider数据集训练，默认参数训练出的模型，需要设置提示词为Sprider中的，回答准确；自定义后的小数据集，训练过程无lass曲线，并且没有效果 HOT 4
- 偏好数据集 Supervised Fine-Tuning 有问题
- 数据集过大导致加载数据集时内存爆掉，似乎在哪里看到可以直接加载tokenize之后的数据进行训练 HOT 1
- 昇腾NPU使用API推理报错 HOT 2
- i dont want to use huggingface, i can i mention my local data path from my computer. 我不想使用Huggingface，我可以提到我电脑上的本地数据路径。 HOT 1
- errors while in finetune intermlm2-chat-20b with qlora 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 llama-factory.