Document RKLLM artifacts and checksums

README.md

@@ -14,32 +14,31 @@ tags:
 
 # Llama-3.2-1B-Instruct-RKLLM
 
-RKLLM-converted versions of Llama 3.2 1B Instruct for deployment on Rockchip RK3576 and RK3588 NPUs.
+RKLLM-converted Llama 3.2 1B Instruct language-model artifacts for Rockchip RK3576 and RK3588 NPUs.
 
-`.rkllm` files require the Rockchip RKLLM runtime and cannot be loaded directly with Transformers, llama.cpp, or Ollama.
+These hardware-specific `.rkllm` files require a compatible Rockchip RKLLM runtime. They are not Transformers checkpoints and cannot be loaded directly with Transformers, llama.cpp, or Ollama.
 
-## Base Model
+## Base model
 
-- Model: Llama 3.2 1B Instruct
-- Author: Meta
-- Original model: [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)
-- Original license: Llama 3.2 Community License
+- Upstream model: [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)
+- License: Llama 3.2 Community License
+- Model type: LLM (text only)
 
-Access to the upstream model is gated. Refer to its model card, license, and acceptable-use policy before using these converted artifacts.
+The upstream model is gated. Review Meta's license and acceptable-use policy before use or redistribution.
 
-## Available Variants
+## Conversion and variants
 
-| Target | File | Quantization |
-| --- | --- | --- |
-| RK3576 | [`Llama-3.2-1B-Instruct_RK3576_w4a16_g128.rkllm`](RK3576/Llama-3.2-1B-Instruct_RK3576_w4a16_g128.rkllm) | W4A16 (g128) |
-| RK3576 | [`Llama-3.2-1B-Instruct_RK3576_w8a8.rkllm`](RK3576/Llama-3.2-1B-Instruct_RK3576_w8a8.rkllm) | W8A8 |
-| RK3588 | [`Llama-3.2-1B-Instruct_RK3588_w8a8.rkllm`](RK3588/Llama-3.2-1B-Instruct_RK3588_w8a8.rkllm) | W8A8 |
+Converted with RKLLM Toolkit 1.3.0. Use a file built for the exact target SoC.
 
-The repository also contains `Llama-3.2-1B-Instruct_data_quant.json`, the calibration data used during conversion.
+| Target | Quantization | File | SHA256 |
+| --- | --- | --- | --- |
+| RK3576 | W4A16 (g128) | [Llama-3.2-1B-Instruct_RK3576_w4a16_g128.rkllm](RK3576/Llama-3.2-1B-Instruct_RK3576_w4a16_g128.rkllm) | `bd6cbbf84e90b63d451e672a542858a5a6aa15ad2b45f83e1b5dbcd944ac3018` |
+| RK3576 | W8A8 | [Llama-3.2-1B-Instruct_RK3576_w8a8.rkllm](RK3576/Llama-3.2-1B-Instruct_RK3576_w8a8.rkllm) | `9c4d103f7c486740ba75605c61a51b80d170df067645360ffad8464b50c764df` |
+| RK3588 | W8A8 | [Llama-3.2-1B-Instruct_RK3588_w8a8.rkllm](RK3588/Llama-3.2-1B-Instruct_RK3588_w8a8.rkllm) | `4403aec1c018c7ebf29c95730336e848aff8824e3be3bd6be7db44b4a4973bad` |
 
-## Usage
+The repository also includes `Llama-3.2-1B-Instruct_data_quant.json`, used as calibration data during conversion.
 
-Download the model variant that matches your target SoC:
+## Usage
 
 ```bash
 hf download HanzoHuang/Llama-3.2-1B-Instruct-RKLLM \
@@ -47,18 +46,12 @@ hf download HanzoHuang/Llama-3.2-1B-Instruct-RKLLM \
   --local-dir Llama-3.2-1B-Instruct-RKLLM
 ```
 
-Load the `.rkllm` file with a compatible RKLLM runtime and apply the Llama 3.2 Instruct chat template in your application.
+Use the Llama 3.2 Instruct chat template with the RKLLM runtime. For Docker deployment, see [Hanzo-Huang/rkllm-docker](https://github.com/Hanzo-Huang/rkllm-docker).
 
 ## Limitations
 
-- These are hardware-specific converted artifacts, not Transformers checkpoints.
-- Runtime, driver, and toolkit compatibility depends on the Rockchip software stack installed on the device.
-- Conversion may change output quality relative to the upstream floating-point model; validate on your own workload.
-
-## License
-
-Use of these converted artifacts remains subject to the Llama 3.2 Community License and applicable upstream terms.
+These are target-specific converted artifacts. Validate quality, memory use, and runtime compatibility on your own Rockchip device.
 
 ## Acknowledgements
 
-Thanks to Meta for releasing Llama 3.2 and to Rockchip and RKLLM contributors for the deployment toolchain.
+Thanks to Meta, Rockchip, and the RKLLM community.