Add SparkBotLLM setup, adaptation and validation writeup

README.md

@@ -8,11 +8,19 @@ license_link: LICENSE
 language: [en]
 pipeline_tag: text-generation
 ---
-# SparkBotLLM 1.7B · initial preview
+# SparkBotLLM 1.7B
 
 A local assistant for DGX Spark setup and local inference, adapted from LiquidAI LFM3 1.7B. Sparkbot supplies the live inspection tools, reviewed actions and dated support references. Model inference can run privately on CPU with a 4K context and one request at a time.
 
-This is a small first adaptation, not a complete or continuously updated authority on NVIDIA hardware or new models. Use hardware tools for measurements and current primary sources for releases. Keep command review enabled.
+SparkBotLLM helps you take the next step with your Spark: check a setup, understand a deployment requirement, or inspect a problem before changing anything. The surrounding Sparkbot dashboard gives it hardware inspection and terminal tools, with owner review for changes.
+
+For current releases, use discovery tools and primary sources. For live clocks, memory and Docker status, use hardware tools. The weights alone cannot inspect your machine.
+
+## Getting started
+
+The model is designed for the [Sparkbot dashboard](https://github.com/x00byte/DGX-Sparkbot). The dashboard and website installation package are being prepared for release; the source repository is currently private. You can run the GGUF independently with a current LFM3-capable llama.cpp build using the command below. No Docker or GPU is required for CPU inference.
+
+Download the GGUF from **Files and versions**. It is approximately 1.05 GB. Start with a 4K context, four CPU threads and one request at a time. This keeps the helper small while your main model uses the GPU.
 
 ## Files and use
 
@@ -24,6 +32,12 @@ Run with a recent LFM3-capable llama.cpp server, for example:
 llama-server --model SparkBotLLM-1.7B-Q4_0.gguf --alias SparkBotLLM --host 127.0.0.1 --port 10004 --ctx-size 4096 --parallel 1 --threads 4 --n-gpu-layers 0 --jinja --chat-template-kwargs '{"enable_thinking":false}'
 ```
 
+## What changed
+
+The base model received a short supervised adaptation focused on DGX Spark support, local inference concepts and choosing the right inspection tool. The application also supplies a dated reference pack; that reference material can be updated independently of the model.
+
+SparkBotLLM is intended to explain requirements, diagnose issues and propose useful next steps. Shell access and deployment automation come from the host application, not from the model file itself.
+
 ## Adaptation and checks
 
 242 authored synthetic support examples, 44 dated support references, LoRA rank 8/alpha 16, assistant-only loss, AdamW learning rate 0.00005. A 192-step run selected step 128 by lowest validation loss. Six domain validation examples were used for selection: mean loss fell from 4.62 to 3.32. They are not an independent test set. Five independent Q4 tool-routing smoke checks passed after export. These narrow checks do not establish broad factual accuracy, safety or reliability. Peak training CUDA allocation was 3.59 GiB. Reports are included.