Request: Add a quantized model to the Arena?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
I assume your `vicuna-13b` in the leaderboard is the full model? Lots of people are experimenting with 5-bit quantized models that can run on a consumer desktop. You don't need to add every single variation that comes out each week, but it would be good to see at least one ([`ggml-old-vic13b-q5_1.bin`](https://huggingface.co/eachadea/ggml-vicuna-13b-1.1/), for instance?) in the arena to see how much performance is lost in the quantization.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Review how the Arena currently represents the full vicuna-13b model and how leaderboard model variants are evaluated. Done means adding a 5-bit quantized model such as ggml-old-vic13b-q5_1.bin and exposing its performance for comparison.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100