Comments (3)
Btlmd
commented on June 12, 2024
我们之前没有在 FastChat 上进行过推理实验。能否给出更详细的报错、不符合预期的场景或者配置？
from agenttuning.
heimy2000
commented on June 12, 2024
用fastchat部署AgentLM-13B，推理的时候格式是乱的，尤其是streaming的模式，每行只有几个字符就切换到下一行了，一个单词被切成了好几个字母或字母组合。如果手动用transformer加载并用gradio展示的话就没有这个问题，用fastchat的debug模式看了一下，用的是LlamaForCausalLM加载的模型，应该没错
老师，请问您是怎么操作的呢
from agenttuning.
ruifengma
commented on June 12, 2024
hi @Btlmd @heimy2000 , 其实就是简单的使用 fastchat.serve.cli 来加载模型进行基础对话，其实没有报错，只是输出的chunk就很奇怪并且不成句，其实你们可以试试看，操作很简单
python3 -m fastchat.serve.cli --model-path AgentTuning/AgentLM
--model-path后面就是加的实际存储的AgentLM权重
from agenttuning.
Related Issues (20)
- AgentTuning 7b evaluate in HH， not expect as paper result HOT 13
- Dataset details 中找不到reward的计算方式 HOT 5
- 通用数据如何筛选 HOT 7
- 除了用docker运行，还有其他方式可以运行AgentLM吗？ HOT 6
- Finetuning with Mistral or Yi? HOT 1
- 关于TRAJECTORY FILTERING问题 HOT 3
- 请问下agentlm-7b最少需要多少显存可以推理 HOT 5
- 期待用 Qwen72B 训练的模型。 HOT 1
- 可以给个简单点的工具调用示例吗 HOT 1
- Can I run AgentInstruct data on the AgentBench? HOT 1
- Can you point to the ShareGPT filtered/cleaned data used? HOT 1
- if it is possible to conduct RLHF from env HOT 1
- 训练数据是如何采样的？ HOT 3
- 貌似hotpotqa测试脚本跑不起来？ HOT 1
- weight decay确定是0.1吗？ HOT 1
- 魔塔上的 AgentInstruct 数据集的 conversation 都是空值
- 请问哪里可以找到工作里对于数据库方面的训练数据 HOT 1
- 本地模型
- 训练数据中指令与模型行为不匹配
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 agenttuning.