Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED
+base_model_relation: quantized
+quantized_by: Atomic-Germ
+pipeline_tag: text-generation
+tags:
+- safetensors
+- qwen3_5_text
+- DuoNeural
+- cybersecurity
+- agentic
+- qlora
+- unsloth
+- qwen3_5
+- obliterated
+- terminal
+- cli
+- reasoning
+- function-calling
+- tool-use
+- text-generation
+- conversational
+- en
+- dataset:oi-uae/cyber-security
+- dataset:hotdogs/uka-cyber-dataset
+- dataset:trend-cybertron/Primus-Reasoning
+- dataset:Lite-Coder/LiteCoder-Terminal-SFT
+- dataset:rajistics/openhands-synthetic-conversations
+- dataset:emirkaanozdemr/bash_command_data_6K
+- dataset:NousResearch/hermes-function-calling-v1
+- dataset:open-thoughts/OpenThoughts3-1.2M
+- base_model:OBLITERATUS/Ornith-1.5-9B-OBLITERATED
+- base_model:finetune:OBLITERATUS/Ornith-1.5-9B-OBLITERATED
+- license:apache-2.0
+- region:us
+---
+# Cyber-Ornith-1.5-9B-NPU2
+
+**OpenFlowLM Q4NX conversion of [`DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED`](https://huggingface.co/DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED)** for AMD XDNA NPU inference.
+
+This repository contains a quantized **Q4NX** port of the model, compiled for the OpenFlowLM (OFLM) runtime. It is **not** a GGUF file.
+
+| Item | Value |
+|------|-------|
+| Source model | [`DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED`](https://huggingface.co/DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED) |
+| Weights | `model.q4nx` (7.11 GB) |
+| Modality | language |
+| OFLM version | `0.1.0` |
+| Converted | 2026-10-03 |
+
+## Install and run
+
+This repository works with `oflm-add`, a small installer that copies the model
+into the OpenFlowLM user directory and registers the tag. It never
+modifies the system OpenFlowLM install.
+
+`pip install oflm-add` or `uv tool install oflm-add`
+
+```bash
+uv tool install oflm-add
+oflm-add Atomic-Germ/Cyber-Ornith-1.5-9B-NPU2 --family qwen3.5 --xclbin-from Cyber-Ornith-1.5-9B-NPU2
+OFLM_CONFIG_PATH="$HOME/.config/oflm/model_list.json" OFLM_XCLBIN_PATH="$HOME/.config/oflm" oflm run Cyber-Ornith-1.5-9B-NPU2
+```
+
+## Files
+
+| File | Description |
+|------|-------------|
+| `model.q4nx` | Quantized weights (Q8_0 / Q4_1 / BF16) |
+| `config.json` | OFLM runtime configuration |
+| `tokenizer.json` | Tokenizer vocabulary |
+| `tokenizer_config.json` | Tokenizer configuration |
+| `chat_template.jinja` | Chat template |
+
+
+---
+
+## Source model card
+
+See the original model card: [DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED](https://huggingface.co/DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED)