Link to deploy:
endpoints.huggingface.co/huggingface/...
endpoints.huggingface.co/huggingface/...
Deploy google/gemma-3-27b-it | Inference Endpoints by Hugging Face
Deploy google/gemma-3-27b-it for image-text-to-text in 1 click.
endpoints.huggingface.co
March 12, 2025 at 11:29 AM
Link to deploy:
endpoints.huggingface.co/huggingface/...
endpoints.huggingface.co/huggingface/...
There’s some deep wisdom in that as well!
December 8, 2024 at 2:38 PM
There’s some deep wisdom in that as well!
Exactly.
Suppose we have an algorithm that is guaranteed to give output according to a structure, with the caveat that it might run out of tokens.
Should this still be classified as structured generation?
Suppose we have an algorithm that is guaranteed to give output according to a structure, with the caveat that it might run out of tokens.
Should this still be classified as structured generation?
December 6, 2024 at 9:42 AM
Exactly.
Suppose we have an algorithm that is guaranteed to give output according to a structure, with the caveat that it might run out of tokens.
Should this still be classified as structured generation?
Suppose we have an algorithm that is guaranteed to give output according to a structure, with the caveat that it might run out of tokens.
Should this still be classified as structured generation?
CUDA libraries..? So they have access to gpus as well? 👀
December 5, 2024 at 7:33 PM
CUDA libraries..? So they have access to gpus as well? 👀
A video series on how to develop, profile and compare cuda kernels would be such a banger.
And allow a lot more tinkerers to enter the field.
And allow a lot more tinkerers to enter the field.
December 5, 2024 at 7:32 PM
A video series on how to develop, profile and compare cuda kernels would be such a banger.
And allow a lot more tinkerers to enter the field.
And allow a lot more tinkerers to enter the field.
Hell yeah 🔥
How would you classify the edge case when running out of tokens?
E.g if it goes into a ”\n” loop and runs out of tokens.
How would you classify the edge case when running out of tokens?
E.g if it goes into a ”\n” loop and runs out of tokens.
December 5, 2024 at 7:29 PM
Hell yeah 🔥
How would you classify the edge case when running out of tokens?
E.g if it goes into a ”\n” loop and runs out of tokens.
How would you classify the edge case when running out of tokens?
E.g if it goes into a ”\n” loop and runs out of tokens.
Interesting, for me it's snappy as hell, maybe things aren't cached as well in Costa Rica? 🤔
December 1, 2024 at 10:15 AM
Interesting, for me it's snappy as hell, maybe things aren't cached as well in Costa Rica? 🤔
pro tip for the borrow-checker, using .clone() everywhere is okay 🙌
December 1, 2024 at 10:13 AM
pro tip for the borrow-checker, using .clone() everywhere is okay 🙌
Or then you can let the model run free in a constrained environment.
I’m tinkering on this: bsky.app/profile/erik...
I’m tinkering on this: bsky.app/profile/erik...
A while ago I started experimenting with compiling the Python interpreter to WASM.
To build a secure, fast, and lightweight sandbox for code execution — ideal for running LLM-generated Python code.
- Send code simply as a POST request
- 1-2ms startup times
github.com/ErikKaum/run...
To build a secure, fast, and lightweight sandbox for code execution — ideal for running LLM-generated Python code.
- Send code simply as a POST request
- 1-2ms startup times
github.com/ErikKaum/run...
GitHub - ErikKaum/runner: Experimental wasm32-unknown-wasi runtime for Python code execution
Experimental wasm32-unknown-wasi runtime for Python code execution - ErikKaum/runner
github.com
November 27, 2024 at 3:53 PM
Or then you can let the model run free in a constrained environment.
I’m tinkering on this: bsky.app/profile/erik...
I’m tinkering on this: bsky.app/profile/erik...
Nice! This is so neat 🙌🏽
November 26, 2024 at 10:23 PM
Nice! This is so neat 🙌🏽