Document RKLLM artifacts and checksums

README.md

@@ -1,6 +1,7 @@
 ---
 license: apache-2.0
 base_model: google/gemma-4-E2B-it
+pipeline_tag: text-generation
 library_name: rkllm
 tags:
 - rkllm
@@ -13,32 +14,32 @@ tags:
 
 # gemma-4-E2B-it-RKLLM
 
-RKLLM-converted versions of Gemma 4 E2B IT for deployment on Rockchip RK3576 and RK3588 NPUs.
+RKLLM-converted Gemma 4 E2B IT 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.
+Important: the upstream Gemma 4 E2B IT model is multimodal/VLM-capable, but this repository contains only the RKLLM language-model binaries. The converted model exposed here is LLM-only: it does not accept images and does not include an RKNN vision encoder.
 
-## Base Model
+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.
 
-- Model: Gemma 4 E2B IT
-- Author: Google
-- Original model: [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it)
-- Original license: Apache-2.0
+## Base model
 
-Refer to the upstream model card for the original model's capabilities, limitations, and acceptable-use guidance.
+- Upstream model: [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it)
+- License: Apache-2.0
+- Upstream type: VLM/multimodal
+- RKLLM type: LLM-only
 
-## Available Variants
+## Conversion and variants
 
-| Target | File | Quantization |
-| --- | --- | --- |
-| RK3576 | [`gemma-4-E2B-it_RK3576_w4a16_g128.rkllm`](RK3576/gemma-4-E2B-it_RK3576_w4a16_g128.rkllm) | W4A16 (g128) |
-| RK3576 | [`gemma-4-E2B-it_RK3576_w8a8.rkllm`](RK3576/gemma-4-E2B-it_RK3576_w8a8.rkllm) | W8A8 |
-| RK3588 | [`gemma-4-E2B-it_RK3588_w8a8.rkllm`](RK3588/gemma-4-E2B-it_RK3588_w8a8.rkllm) | W8A8 |
+Converted with RKLLM Toolkit 1.3.0. Use a file built for the exact target SoC.
 
-The repository also contains `gemma-4-E2B-it_data_quant.json`, the calibration data used during conversion.
+| Target | Quantization | File | SHA256 |
+| --- | --- | --- | --- |
+| RK3576 | W4A16 (g128) | [gemma-4-E2B-it_RK3576_w4a16_g128.rkllm](RK3576/gemma-4-E2B-it_RK3576_w4a16_g128.rkllm) | `973008fd7ebed81e2a26dcf7dcc1c28fde631837e3e021c7f3007d6e82647165` |
+| RK3576 | W8A8 | [gemma-4-E2B-it_RK3576_w8a8.rkllm](RK3576/gemma-4-E2B-it_RK3576_w8a8.rkllm) | `b7357c01fcd51c8f896f06ee3a3746bc233031abd04e2fa0cebb5908b1382a01` |
+| RK3588 | W8A8 | [gemma-4-E2B-it_RK3588_w8a8.rkllm](RK3588/gemma-4-E2B-it_RK3588_w8a8.rkllm) | `ae81d1e37eb54b40d2d366ef622a0c05acfb15537272e982efc1dfdd60557979` |
 
-## Usage
+The repository also includes `gemma-4-E2B-it_data_quant.json`, used as calibration data during conversion.
 
-Download the model variant that matches your target SoC:
+## Usage
 
 ```bash
 hf download HanzoHuang/gemma-4-E2B-it-RKLLM \
@@ -46,14 +47,12 @@ hf download HanzoHuang/gemma-4-E2B-it-RKLLM \
   --local-dir gemma-4-E2B-it-RKLLM
 ```
 
-Load the `.rkllm` file with a compatible RKLLM runtime. Use the correct prompt formatting for the instruction-tuned upstream model.
+Run the file with the RKLLM runtime and the upstream Gemma instruction prompt format. 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.
+Vision input is not supported by these artifacts. Conversion can change output quality relative to the upstream model; validate the result on your target device.
 
 ## Acknowledgements
 
-Thanks to Google for releasing Gemma 4 E2B IT and to Rockchip and RKLLM contributors for the deployment toolchain.
+Thanks to Google, Rockchip, and the RKLLM community.