-
Trying to get an overview of specification and diagnostic tests and plots by model categories.
**general**
- variable addition score_test
- reset type tests
- PIT type test and plots, gof (con…
-
TensorFlow probability has multiple features of interest for us:
* Distributions. They could replace our custom implementations (Gaussian, GaussianMC) and
* Optimisers and samplers. We could hija…
-
Hello. I'm struggling with replicating the [reported perplexity](https://github.com/ggerganov/llama.cpp/discussions/2352) (~6) for LLaMa-2-7b.
I am using this simple code snippet:
```
import evalu…
-
使用的是秋叶整合包，直接搜索报错说让将torch回退到21coda118，我也不是很懂，直接在整合包里回退了，
之前还有别的状况，我在custom_nodes下按照主页里的方法用指令下载依赖后出现闪退，我按照其他教程…
-
I was just thinking, though our pointer-generator implementation(s) take care to encode features separately so that they are not used in the attention distribution for the pointer probabilities, I thi…
-
It would be cool to implement a soft tokenizer so we can use it in some of our actual models. The soft tokenizer considers overlap between the query and the universe (vocab). Using this information, w…
-
Hi, just a detail for the occurrence indicator graphs Y-axis legend: Occupancy, in principle, is mostly used for the probability that a site is occupied (and expressed between 0 and 1) cf. site occupa…
-
## Issue description
torch.multinomial only works on single and double dimension tensors, without giving ability for choosing probability dimension.
Thus, multinomial is not directly usable on rnn…
-
It's not clear from the examples in the Readme and from the [paper](https://arxiv.org/pdf/2311.14838.pdf) what would be a good first choice of the modifiers' probabilities to start with. I understand …
-
Hello,
I've been exploring the predictor_proba function defined in sklearn.py at [this location](https://github.com/postgresml/postgresml/blob/master/pgml-extension/src/bindings/sklearn/sklearn.py#…