tensorblock
/

starcoder2-15b-GGUF

@@ -87,8 +87,16 @@ This repo contains GGUF format model files for [bigcode/starcoder2-15b](https://
 The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
 ## Prompt template
 ```
 ```
@@ -97,18 +105,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
-| [starcoder2-15b-Q2_K.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q2_K.gguf) | Q2_K | 5.768 GB | smallest, significant quality loss - not recommended for most purposes |
-| [starcoder2-15b-Q3_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q3_K_S.gguf) | Q3_K_S | 6.507 GB | very small, high quality loss |
-| [starcoder2-15b-Q3_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q3_K_M.gguf) | Q3_K_M | 7.492 GB | very small, high quality loss |
-| [starcoder2-15b-Q3_K_L.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q3_K_L.gguf) | Q3_K_L | 8.350 GB | small, substantial quality loss |
-| [starcoder2-15b-Q4_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q4_0.gguf) | Q4_0 | 8.443 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
-| [starcoder2-15b-Q4_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q4_K_S.gguf) | Q4_K_S | 8.532 GB | small, greater quality loss |
-| [starcoder2-15b-Q4_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q4_K_M.gguf) | Q4_K_M | 9.183 GB | medium, balanced quality - recommended |
-| [starcoder2-15b-Q5_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q5_0.gguf) | Q5_0 | 10.265 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
-| [starcoder2-15b-Q5_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q5_K_S.gguf) | Q5_K_S | 10.265 GB | large, low quality loss - recommended |
-| [starcoder2-15b-Q5_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q5_K_M.gguf) | Q5_K_M | 10.646 GB | large, very low quality loss - recommended |
-| [starcoder2-15b-Q6_K.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q6_K.gguf) | Q6_K | 12.201 GB | very large, extremely low quality loss |
-| [starcoder2-15b-Q8_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/tree/main/starcoder2-15b-Q8_0.gguf) | Q8_0 | 15.800 GB | very large, extremely low quality loss - not recommended |
 ## Downloading instruction

 The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
+<div style="text-align: left; margin: 20px 0;">
+    <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
+        Run them on the TensorBlock client using your local machine ↗
+    </a>
+</div>
 ## Prompt template
 ```
 ```
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
+| [starcoder2-15b-Q2_K.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q2_K.gguf) | Q2_K | 5.768 GB | smallest, significant quality loss - not recommended for most purposes |
+| [starcoder2-15b-Q3_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q3_K_S.gguf) | Q3_K_S | 6.507 GB | very small, high quality loss |
+| [starcoder2-15b-Q3_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q3_K_M.gguf) | Q3_K_M | 7.492 GB | very small, high quality loss |
+| [starcoder2-15b-Q3_K_L.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q3_K_L.gguf) | Q3_K_L | 8.350 GB | small, substantial quality loss |
+| [starcoder2-15b-Q4_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q4_0.gguf) | Q4_0 | 8.443 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [starcoder2-15b-Q4_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q4_K_S.gguf) | Q4_K_S | 8.532 GB | small, greater quality loss |
+| [starcoder2-15b-Q4_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q4_K_M.gguf) | Q4_K_M | 9.183 GB | medium, balanced quality - recommended |
+| [starcoder2-15b-Q5_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q5_0.gguf) | Q5_0 | 10.265 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [starcoder2-15b-Q5_K_S.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q5_K_S.gguf) | Q5_K_S | 10.265 GB | large, low quality loss - recommended |
+| [starcoder2-15b-Q5_K_M.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q5_K_M.gguf) | Q5_K_M | 10.646 GB | large, very low quality loss - recommended |
+| [starcoder2-15b-Q6_K.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q6_K.gguf) | Q6_K | 12.201 GB | very large, extremely low quality loss |
+| [starcoder2-15b-Q8_0.gguf](https://huggingface.co/tensorblock/starcoder2-15b-GGUF/blob/main/starcoder2-15b-Q8_0.gguf) | Q8_0 | 15.800 GB | very large, extremely low quality loss - not recommended |
 ## Downloading instruction