Update README.md

README.md

@@ -33,6 +33,10 @@ datasets:
 - jukofyork/instruction-responses-500MB
 ---
 
+**NOTE**: Read the [Control Adapter documentation](https://github.com/jukofyork/qlora-pipe-lite/blob/main/docs/ControlAdapters.md) for implementation details.
+
+---
+
 Trained via [qlora-pipe-lite](https://github.com/jukofyork/qlora-pipe-lite):
 
 ```toml
@@ -111,7 +115,7 @@ dataset_path = '/mnt/datasets/instruction-refusals-500MB/*.json'
 control_class = -1
 ```
 
-using ~200M total tokens from:
+using ~200M tokens (ie: ~100M positive and ~100M negative) from:
 
 - [jukofyork/instruction-responses-500MB](https://huggingface.co/datasets/jukofyork/instruction-responses-500MB)
 - [jukofyork/instruction-refusals-500MB](https://huggingface.co/datasets/jukofyork/instruction-refusals-500MB)
@@ -130,4 +134,8 @@ The control adapter was then converted to a LoRA using [control_adapter_to_lora.
 
 [jukofyork/command-a-03-2025-uncut-lora](https://huggingface.co/jukofyork/command-a-03-2025-uncut-lora)
 
-and then merged using the [merge-lora](https://huggingface.co/spaces/jukofyork/merge-lora) space.
+and then merged using the [merge-lora](https://huggingface.co/spaces/jukofyork/merge-lora) space.
+
+---
+
+See [https://huggingface.co/jukofyork/command-a-03-2025-uncut-lora-gguf](https://huggingface.co/jukofyork/command-a-03-2025-uncut-lora-gguf) for a LoRA in GGUF format that can be used with the `--lora` option on top of the base [CohereLabs/c4ai-command-a-03-2025](https://huggingface.co/CohereLabs/c4ai-command-a-03-2025) to get the same effect.