Add GGUF quants

Gemma-3-27B-Roblox-Luau-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f407c6a06851b66cc4deb718c52d640387c78ed8b89062788cb1bcbb46f7874d
+size 14043341568

Gemma-3-27B-Roblox-Luau-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431dc15aad46a47e9f7fe9b3945096c12489b8194c54df4ad34d8623c99bb1d3
+size 17339606400

Gemma-3-27B-Roblox-Luau-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2fbd799e6ca97a78a96209fbcf00b82f593e06f23b7e99bf69a1d9af0373b1
+size 20240797056

Gemma-3-27B-Roblox-Luau-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eedb94c6134dbc9a60760c1930cafda228b4520007d69244508c12e0efdef9e
+size 23323312128

Gemma-3-27B-Roblox-Luau-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7dd57b5376e98d53ff78614e4cb84f5fd1d89d7028a8d9764baf7aa36ef3c40
+size 30205704960

README.md

@@ -18,3 +18,13 @@ datasets:
 # Gemma-3-27B-Roblox-Luau
 
 A fine tune of [google/gemma-3-27b-it](google/gemma-3-27b-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.
+
+Available quants:
+
+| Quant  | Size    | Notes |
+| ------ | ------- | ----- |
+| Q8_O   | 30.21GB | High resource use, but generally acceptable. Use only when accuracy is crucial. |
+| Q6_K   | 23.32GB | Uses Q6_K for all tensors. Good for high end GPUs. |
+| Q5_K_M | 20.24GB | Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K |
+| Q4_K_M | 17.34GB | **Recommended.** Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K |
+| Q3_K_M | 14.04GB | Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K. Quality is noticeably degraded. |