Marnix Van Soom

Use demo with finetuned checkpoint

1

Is it possible to use a finetuned checkpoint in the demo, specifically for ActivityNet-QA? Right now the API for finetuned models is kinda locked away in the train and eval...

Hi, just an idea, feel free to close. Would it be possible to write a reversible arithmetic encoder? Such that the inverse of the encoder is the decoder. And you...

Trying to deploy via JCloud

7

I installed `pip install open_gpt_torch` today. The `opengpt serve stabilityai/stablelm-tuned-alpha-3b --precision fp16 --device_map balanced` command fails because `open_gpt/resources/flow.yml.jinja2` cannot be found. I think it might be missing from the `pip`...

I installed the repo for Visualized-BGE following the instructions at `FlagEmbedding/visual/README.md` on CPU. I downloaded the weights from HF. When executing the example code in the README: ```python ####### Use...

Very happy to hear about the funding from Alan Turing Institute! I was wondering if there is still interest for working on [the NestedSamplers integration](https://github.com/TuringLang/NestedSamplers.jl/issues/29), as this is possibly a...

Implement `quantile(model(), u)`?

4

Sampling from priors works perfectly: ```julia using Turing # v0.21.10 @model function test() x ~ Normal() y ~ Uniform() return 0. end rand(test()) # (x = 1.310427089277206, y = 0.2538675545828133)...

 [Unit conversion error causes NASA Mars Orbiter to blow up.](https://www.youtube.com/watch?v=Iq_r7IcNmUk&t=495s)