Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -41,6 +41,8 @@ model-index:
|
|
| 41 |
|
| 42 |
# Roblox Luau Mistral 7B — SFT
|
| 43 |
|
|
|
|
|
|
|
| 44 |
A **supervised fine-tuned** LoRA adapter for generating production-ready Roblox Luau scripts. Built on [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) and trained on curated Luau code from [the-luau-stack](https://huggingface.co/datasets/TorpedoSoftware/the-luau-stack) + Claude-generated gold examples.
|
| 45 |
|
| 46 |
**Part of the [Roblox Luau Code Generator](https://github.com/squaredrblx-lang/roblox-luau-codegen) project for the W&B Fine-Tuning Hackathon.**
|
|
|
|
| 41 |
|
| 42 |
# Roblox Luau Mistral 7B — SFT
|
| 43 |
|
| 44 |
+
> **Recommended:** Use the improved [RFT version](https://huggingface.co/squaredcuber/roblox-luau-mistral-7b-rft) instead. The RFT model scores higher across all dimensions (+5% composite) thanks to reinforcement fine-tuning with Claude-as-judge reward scoring.
|
| 45 |
+
|
| 46 |
A **supervised fine-tuned** LoRA adapter for generating production-ready Roblox Luau scripts. Built on [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) and trained on curated Luau code from [the-luau-stack](https://huggingface.co/datasets/TorpedoSoftware/the-luau-stack) + Claude-generated gold examples.
|
| 47 |
|
| 48 |
**Part of the [Roblox Luau Code Generator](https://github.com/squaredrblx-lang/roblox-luau-codegen) project for the W&B Fine-Tuning Hackathon.**
|