Text Classification
GGUF
English
rknn
rknn3
rk1828
rk1820
rockchip
npu
edge-ai
kev
decision
w4a16
Eval Results (legacy)
conversational
Instructions to use jj90/Kev-0.8B-RKNN3-RK1828 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use jj90/Kev-0.8B-RKNN3-RK1828 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf jj90/Kev-0.8B-RKNN3-RK1828 # Run inference directly in the terminal: llama cli -hf jj90/Kev-0.8B-RKNN3-RK1828
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf jj90/Kev-0.8B-RKNN3-RK1828 # Run inference directly in the terminal: llama cli -hf jj90/Kev-0.8B-RKNN3-RK1828
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf jj90/Kev-0.8B-RKNN3-RK1828 # Run inference directly in the terminal: ./build/bin/llama cli -hf jj90/Kev-0.8B-RKNN3-RK1828
Use Docker
docker model run hf.co/jj90/Kev-0.8B-RKNN3-RK1828
- Llama new
- LM Studio
- Jan
- Ollama
How to use jj90/Kev-0.8B-RKNN3-RK1828 with Ollama:
ollama run hf.co/jj90/Kev-0.8B-RKNN3-RK1828
- Unsloth Desktop
- Pi
How to use jj90/Kev-0.8B-RKNN3-RK1828 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf jj90/Kev-0.8B-RKNN3-RK1828
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "jj90/Kev-0.8B-RKNN3-RK1828" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use jj90/Kev-0.8B-RKNN3-RK1828 with Docker Model Runner:
docker model run hf.co/jj90/Kev-0.8B-RKNN3-RK1828
- Lemonade
How to use jj90/Kev-0.8B-RKNN3-RK1828 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull jj90/Kev-0.8B-RKNN3-RK1828
Run and chat with the model
lemonade run user.Kev-0.8B-RKNN3-RK1828-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use jj90/Kev-0.8B-RKNN3-RK1828 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf jj90/Kev-0.8B-RKNN3-RK1828
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default jj90/Kev-0.8B-RKNN3-RK1828
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use jj90/Kev-0.8B-RKNN3-RK1828 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf jj90/Kev-0.8B-RKNN3-RK1828
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "jj90/Kev-0.8B-RKNN3-RK1828" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Add start.cmd
Browse files- rknn/start.cmd +46 -0
rknn/start.cmd
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
@echo off
|
| 2 |
+
rem =====================================================================
|
| 3 |
+
rem Kev-0.8B (Qwen3.5-0.8B + Kev LoRA, merged) for RK1828
|
| 4 |
+
rem Converted with rknn3-model-zoo/examples/Qwen3_5 pipeline.
|
| 5 |
+
rem Arguments are identical to the official rkllm3-server command line,
|
| 6 |
+
rem so you can copy/paste straight from the SDK docs.
|
| 7 |
+
rem
|
| 8 |
+
rem IMPORTANT: keep this file pure ASCII. cmd.exe reads .cmd in the OEM
|
| 9 |
+
rem code page (936 on zh-CN); non-ASCII bytes break the ^ continuation
|
| 10 |
+
rem and the whole command line gets truncated.
|
| 11 |
+
rem
|
| 12 |
+
rem Same tokenizer/vocab as Qwen3.5-0.8B (LoRA does not touch the vocab).
|
| 13 |
+
rem =====================================================================
|
| 14 |
+
setlocal
|
| 15 |
+
if "%RK_HOST%"=="" set RK_HOST=0.0.0.0
|
| 16 |
+
if "%RK_PORT%"=="" set RK_PORT=8888
|
| 17 |
+
|
| 18 |
+
rem Locate the RKNN3 runtime. Two layouts are supported:
|
| 19 |
+
rem <repo>\runtime\rknn3_110 <- this repo as downloaded
|
| 20 |
+
rem <package>\runtime\rknn3_110 <- rk1828-console\models\<model>\
|
| 21 |
+
set "RT=%~dp0..\runtime\rknn3_110"
|
| 22 |
+
if not exist "%RT%\bin" set "RT=%~dp0..\..\runtime\rknn3_110"
|
| 23 |
+
if not exist "%RT%\bin" if not "%RK_RUNTIME%"=="" set "RT=%RK_RUNTIME%"
|
| 24 |
+
if not exist "%RT%\bin" goto no_runtime
|
| 25 |
+
|
| 26 |
+
set "PATH=%RT%\bin;%RT%\lib;%PATH%"
|
| 27 |
+
cd /d "%~dp0"
|
| 28 |
+
goto run
|
| 29 |
+
|
| 30 |
+
:no_runtime
|
| 31 |
+
echo [start.cmd] RKNN3 runtime not found (rkllm3-server.exe missing).
|
| 32 |
+
echo [start.cmd] looked in:
|
| 33 |
+
echo [start.cmd] %~dp0..\runtime\rknn3_110
|
| 34 |
+
echo [start.cmd] %~dp0..\..\runtime\rknn3_110
|
| 35 |
+
echo [start.cmd] Put RKNN3 v1.1.0 there, or set RK_RUNTIME to that folder.
|
| 36 |
+
echo [start.cmd] See docs\DEPLOY.md
|
| 37 |
+
endlocal
|
| 38 |
+
exit /b 1
|
| 39 |
+
|
| 40 |
+
:run
|
| 41 |
+
rkllm3-server -m "Kev-0.8B.rknn" --weight "Kev-0.8B.weight" ^
|
| 42 |
+
--vocab "Kev-0.8B.tokenizer.gguf" --embed "Kev-0.8B.embed.bin" --host "%RK_HOST%" ^
|
| 43 |
+
--port "%RK_PORT%" -c 0 --n_predict 1024 --top-k 20 --top-p 0.9 --temp 1.0 --repeat-penalty 1.3
|
| 44 |
+
|
| 45 |
+
endlocal
|
| 46 |
+
exit /b 0
|