Comments (4)
@zhaochenyang20 just published 0.10.0, can you retry with that version? It's not much progress with the model you're using though, but it does not error anymore.
With your example I get {"name": ":"}
from jsonformer.
Unfortunately I think "t5-small" is a bit too small, the model isn't very good at following JSON conventions. it would work in theory, but as above, it seems to want to generate things like {"name": " "}
, since we chop/stop at the first generated "
I did revamp the string generation logic to include a start quote in the prompt, removing the requirement that the model generates the start quote. This should make it less brittle, but in order to get sensible outputs, I think going larger on the model is your best bet @zhaochenyang20
from jsonformer.
Thanks!
from jsonformer.
I will see if this works out. And here is a related paper for you:
https://arxiv.org/abs/2304.14293
from jsonformer.
Related Issues (20)
- Make `Jsonformer` derive from `PreTrainedModel`
- Description of keys
- ctransformers / GGML support HOT 6
- Need to support Generation Config for model generation parameters
- allow for do_sample=True HOT 1
- High VRam Requirement HOT 3
- Json Former Causing High V-Memory Usage and Error with Increasing Token Size HOT 1
- Error in logits_processors.py - OutputNumbersTokens().__call__() for some models HOT 2
- Supporting InferenceClient
- AWQ RuntimeError HOT 2
- Documentation for returning an array of objects HOT 10
- Issue with array response HOT 1
- feature pairity with openai function calling
- Support for GPTQ models
- Support for LLaVa HOT 1
- compatibility with Gemini
- Infinite recursion bug when calling generate_number HOT 1
- How to specify a schema where an object can be any key-value combination
- Support nullable in case of not found sub object HOT 1
- Failed in: RuntimeError: The expanded size of the tensor (151936) must match the existing size (151646) at non-singleton dimension 1. Target sizes: [1, 151936]. Tensor sizes: [151646]
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 jsonformer.