Initial upload

README.md

@@ -0,0 +1,40 @@
+---
+license: mit
+tags:
+- gguf
+- llama.cpp
+- q4_k_m
+- cypherium
+- cph
+- local-ai
+datasets:
+- cypherium_raw
+language:
+- en
+- ja
+pipeline_tag: text-generation
+---
+
+# CPH-Community-7B (Q4_K_M)
+
+A compact 7B-model fine-tuned for **Cypherium blockchain operations**, validator support, node configuration, RPC troubleshooting, and general-purpose lightweight reasoning.
+
+This model is optimized for **CPU-only inference** using `llama.cpp` and provides fast responses on low-resource servers such as VPS instances (2–6 vCPUs, 8–16GB RAM).
+
+## Model Description
+
+- **Base model:** Qwen2-7B  
+- **Fine-tuning:** QLoRA  
+- **Domain:** Cypherium blockchain RPC, node operations, validator troubleshooting  
+- **Format:** GGUF (`Q4_K_M`)  
+- **Intended use:** lightweight on-device assistant for Cypherium node operators
+
+## Example Inference Command (llama.cpp)
+
+```bash
+./llama-cli \
+  -m cph-community-7b-q4_k_m.gguf \
+  -c 4096 \
+  -n 256 \
+  --system-prompt "You are a helpful Cypherium assistant." \
+  --prompt "Explain how to resync a Cypherium validator node."