Comments (3)
Alcanderian
commented on July 27, 2024
1
bloom，whisper目前还没有官方model zoo支持，如果需要转模型需要先自己用pmx算子构建模型，再进行导出，或者等待我们官方的model zoo进行相应的模型支持。param.json每个模型会有少许不一样，hf上可能是config.json
from ppl.pmx.
maiquanshen
commented on July 27, 2024
bloom，whisper目前还没有官方model zoo支持，如果需要转模型需要先自己用pmx算子构建模型，再进行导出，或者等待我们官方的model zoo进行相应的模型支持。param.json每个模型会有少许不一样，hf上可能是config.json
我看大部分的模型都没有tokenizer.pth文件，更多的是tokenizer.json 你们的pmx算子构建模型时支持这个json文件输入的吗？
from ppl.pmx.
Alcanderian
commented on July 27, 2024
bloom，whisper目前还没有官方model zoo支持，如果需要转模型需要先自己用pmx算子构建模型，再进行导出，或者等待我们官方的model zoo进行相应的模型支持。param.json每个模型会有少许不一样，hf上可能是config.json
我看大部分的模型都没有tokenizer.pth文件，更多的是tokenizer.json 你们的pmx算子构建模型时支持这个json文件输入的吗？
目前PMX偏向于类似hf的单模型单文件夹支持，一般模型都会有tokenizer.model，目前主要支持这种输入，json可以按各个模型的需求进行相应的调整
from ppl.pmx.
Related Issues (10)
- Use A10 to export llama 13B model OOM. HOT 1
- TYPO in “ppl.pmx/docs/operators/dynamic_batching/MultiHeadAttention.md” HOT 2
- 转换llama2 70B模型时遇到的问题 HOT 4
- baichuan13B static/dynamic batching 生成一定长度的句子之后结果出现分歧 HOT 1
- 补充RoPE2D dynamic batching算子文档
- 文档内显示支持qwen1.5，但实际转换报错。 HOT 1
- Good first issue HOT 3
- [LLaMA2-7b] Warning: The shape inference of opmx::ParallelEmbedding type is missing, so it may result in wrong shape inference for the exported graph. Please consider adding it in symbolic function. (function UpdateReliable) HOT 1
- 为什么使用llama脚本转换qwen1.5权重文件，转出来的文件是model.pth和opmx_params.json两个文件 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 ppl.pmx.