Delete README.md

README.md

@@ -1,43 +0,0 @@
----
-library_name: optimum
-tags:
-- intel
-- openvino
-- optimum
-- minicpm
-- tiny-model
-license: apache-2.0
-base_model: openbmb/MiniCPM-o-2_6
----
-
-
-# Tiny-Random-MiniCPM-o-2_6
-
-This is a **tiny random version** of the [MiniCPM-o-2_6](https://huggingface.co/openbmb/MiniCPM-o-2_6) architecture, specifically designed for **integration testing and CI/CD pipelines** in the `optimum-intel` repository.
-
-## Project Goal
-The primary objective of this model is to provide a lightweight alternative for architectural validation and OpenVINO export testing within the `optimum-intel` framework. It replaces larger weights (~5GB+) with a minimal footprint (~0.8MB) while maintaining identical architectural metadata.
-
-## Model Description
-- **Architecture:** Qwen2-based (MiniCPM-o-2.6)
-- **Parameters:** ~1.2M
-- **Hidden Layers:** 2
-- **Hidden Size:** 64
-- **Intermediate Size:** 128
-- **Vocabulary Size:** 1000
-
-## Performance Benchmarks
-Validated on Windows (CPU) using the `optimum-intel` pipeline:
-- **Disk Footprint:** 0.77 MB
-- **PyTorch Load Time:** 0.07s
-- **RAM Usage (Incr.):** ~1.93 MB
-- **OpenVINO Compilation Time:** 4.80s
-- **Compatibility:** Fully verified for `OVModelForCausalLM` and `OVModelForVisualCausalLM`.
-
-## Usage
-```python
-from optimum.intel.openvino import OVModelForVisualCausalLM
-from transformers import AutoProcessor
-
-model_id = "h0witended/tiny-random-MiniCPM-o-2_6"
-model = OVModelForVisualCausalLM.from_pretrained(model_id, trust_remote_code=True)