Will Kurt

icon indicating a website link countbayesie.com icon indicating an email [email protected]

icon location Seattle, WA icon location AI Engineer and author of "Bayesian Statistics the Fun Way" (No Starch, 2019) and "Get Programming with Haskell" (Manning, 2018).

Results 3 issues of Will Kurt

ENH: pd.get_dummies should not default to dtype np.uint8

18 comment

I was caught by surprise the other day when doing some vector subtraction when using pd.get_dummies. The issue is that the default dtype is np.uint8 which means that cases where...

Enhancement
Needs Discussion
good first issue

Add generic function calling support for any open model.

2 comment

# Function Calling for Any Open Model Based on the work in the post [Beating GPT-4 with Open Models](https://blog.dottxt.co/oss-v-gpt4.html) where we implement function calling for a variety of open models...

llama_cpp - JSON fails to generate when using Pydantic model with models.llama_cpp

7 comment

### Describe the issue as clearly as possible: When using `models.llamacpp` and creating JSON using a Pydantic model I get an error when generating the first result (see code to...

bug