Update README.md

README.md

@@ -8,11 +8,24 @@ license: mit
 
 Source model: https://huggingface.co/BAAI/bge-base-en-v1.5
 
-Quantization types:
-- F32 (436 MB)
-- F16 (219 MB)
-- Q8_0 (118 MB)
-- Q4_K_M (68 MB)
+Quantized and unquantized embedding models for use with `llama.cpp`.
+
+<br/>
+
+# Files Available
+
+<div style="width: 500px; margin: 0;">
+
+| Filename | Quantization | Size |
+|:-------- | ------------ | ---- |
+| [bge-base-en-v1.5-f32.gguf](https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf/blob/main/bge-base-en-v1.5-f32.gguf) | F32 | 436 MB |
+| [bge-base-en-v1.5-f16.gguf](https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf/blob/main/bge-base-en-v1.5-f16.gguf) | F16 | 219 MB |
+| [bge-base-en-v1.5-q8_0.gguf](https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf/blob/main/bge-base-en-v1.5-q8_0.gguf) | Q8_0 | 118 MB |
+| [bge-base-en-v1.5-q4_k_m.gguf](https://huggingface.co/CompendiumLabs/bge-base-en-v1.5-gguf/blob/main/bge-base-en-v1.5-q4_k_m.gguf) | Q4_K_M | 68 MB |
+
+</div>
+
+<br/>
 
 # Inference