ddh0
/

Starling-LM-10.7B-beta

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

ddh0 commited on Apr 5

Commit

22e5665

•

1 Parent(s): 7f80a3d

Update README.md

Files changed (1) hide show

README.md +12 -14

README.md CHANGED Viewed

@@ -10,17 +10,15 @@ This is Starling-LM-10.7B-beta, a depth-upscaled version of [Nexusflow/Starling-
 This model is intended to be used as a drop-in upgrade from the original 7 billion parameter model.
-# exllama (Thanks to [blockblockblock](https://huggingface.co/blockblockblock)))
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw2.5
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw3
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw3.5
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw3.7
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw4
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw4
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw4.4
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw4.6
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw4.8
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw5
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw5.5
-https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw6

 This model is intended to be used as a drop-in upgrade from the original 7 billion parameter model.
+# ExLlamaV2 quantizations (courtesy of [blockblockblock](https://huggingface.co/blockblockblock))
+- [2.5 bpw](https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw2.5)
+- [3 bpw](https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw3)
+- [3.5 bpw](https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw3.5)
+- [3.7 bpw](https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw3.7)
+- [4 bpw](https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw4)
+- [4.4 bpw](https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw4.4)
+- [4.6 bpw](https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw4.6)
+- [4.8 bpw](https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw4.8)
+- [5 bpw](https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw5)
+- [5.5 bpw](https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw5.5)
+- [6 bpw](https://huggingface.co/blockblockblock/Starling-LM-10.7B-beta-bpw6)