31 lines
1.4 KiB
Markdown
31 lines
1.4 KiB
Markdown
---
|
|
license: gemma
|
|
license_link: https://ai.google.dev/gemma/terms
|
|
base_model: google/gemma-3-1b-it
|
|
finetuned_by: boatbomber
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- chat
|
|
- roblox
|
|
- luau
|
|
language:
|
|
- en
|
|
datasets:
|
|
- boatbomber/roblox-info-dump
|
|
- boatbomber/the-luau-stack
|
|
---
|
|
|
|
# Gemma-3-1B-Roblox-Luau
|
|
|
|
A fine tune of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) using [boatbomber/roblox-info-dump](https://huggingface.co/datasets/boatbomber/roblox-info-dump) and [boatbomber/the-luau-stack](https://huggingface.co/datasets/boatbomber/the-luau-stack) for Roblox domain knowledge.
|
|
|
|
This is intended to be used for speculative decoding with [boatbomber/Gemma-3-27B-Roblox-Luau](https://huggingface.co/boatbomber/Gemma-3-27B-Roblox-Luau). It can be used standalone in memory constrained environments, but is not nearly as capable as the 27B model as it has so few weights that it cannot learn the same level of detail.
|
|
|
|
Available quants:
|
|
|
|
| Quant | Size | Notes |
|
|
| ----- | ---- | ----- |
|
|
| Q8_O | 1.39GB | High resource use, but generally acceptable. Use when accuracy is crucial. |
|
|
| Q5_K_M | 1.08GB | **Recommended.** Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K |
|
|
| Q3_K_M | 0.89GB | Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K. Quality is noticeably degraded. |
|