Looks like Gemma 3 27b is quite creative in fictional scenarios.

https://garden.tcsenpai.com/bookmarks/ai/ai-convos-notes/gem...

Underrated. And magnificent.

I like this. I am imagining a companion extension for chrome/ff that uses you-get as a backend to implement it in a seamless way. Forward thinking idea: imagine going on youtube and have you-get extension bypass the youtube player and playing the content directly without ads. When I say youtube I might also say any other platform.

Sounds like FastStream Video Player

https://addons.mozilla.org/en-US/firefox/addon/faststream/?u...

This is surely useful right now. I wonder what will happens to all the nice X11 tools once Wayland (hopefully soon) will be the golden standard. There are options to enable X11 behaviors in Wayland but I guess that is just a fallback to the insecure implementation.

Update: v 1.1 is out!

- # Changelog

## [1.1] - 2024-03-19

### Added - New `model_tokens.json` file containing token limits for various Ollama models. - Dynamic token limit updating based on selected model in options. - Automatic loading of model-specific token limits from `model_tokens.json`. - Chunking and recursive summary for long pages - Better handling of markdown returns

### Changed - Updated `manifest.json` to include `model_tokens.json` as a web accessible resource. - Modified `options.js` to handle dynamic token limit updates: - Added `loadModelTokens()` function to fetch model token data. - Added `updateTokenLimit()` function to update token limit based on selected model. - Updated `restoreOptions()` function to incorporate dynamic token limit updating. - Added event listener for model selection changes.

### Improved - User experience in options page with automatic token limit updates. - Flexibility in handling different models and their respective token limits.

### Fixed - Potential issues with incorrect token limits for different models.

I applied (for now) a pre-filled table with a 4096 default limit. Users can also specify an upper or lower limit from the UI directly now. Added chunk and recursive summarization too.

Hi! This was a good suggestion! I implemented it in v 1.1 which is already out :)

Speaking of, I made also a youtube summarizer at https://github.com/tcsenpai/youlama

TIL, I am experimenting with PageAssist right now

Personally I use llama3.1:8b or mistral-nemo:latest which have a decent contex window (even if it is less than the commercial ones usually). I am working on a token calculator / division of the content method too but is very early

why not llama3.2:3B? it has fairly large context window too

I assume because the 8B model is smarter than the 3B model; it outperforms it on almost every benchmark: https://huggingface.co/meta-llama/Llama-3.2-3B

If you have the compute, might as well use the better model :)

The 3.2 series wasn't the kind of leap that 3.0 -> 3.1 was in terms of intelligence; it was just:

1. Meta releasing multimodal vision models for the first time (11B and 90B), and

2. Meta releasing much smaller models than the 3.1 series (1B and 3B).