Update README.md

README.md

@@ -1,5 +1,3 @@
-<img src="assets/banner.jpg" alt="Logo" style="border-radius: 30px; width: 100%;">
-
 Energy-efficient kernels & inference engine for phones. 
 
 ## Why Cactus?
@@ -199,15 +197,6 @@ python3 tools/convert_hf.py nomic-ai/nomic-embed-text-v2-moe weights/nomic/ --pr
 
 Simply replace the weight path `tests/test_engine.cpp` with your choice.
 
-## Roadmap:
-- Llama, LFM, SmolVLM, Whisper, Kitten, Neuphonic
-- Python tools for porting any Torch/JAX to cactus
-- GPTQ & NPU/DSP/ISP for high-end phones 
-
 ## Limitations
 While Cactus can be used for all Apple devices including Macbooks, for computers/AMD/Intel/Nvidia generally, 
-please use HuggingFace, Llama.cpp, Ollama, vLLM, MLX. They're built for those, support x86, and are all great! 
-
-## Contributing
-
-We welcome contributions! Please see our [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
+please use HuggingFace, Llama.cpp, Ollama, vLLM, MLX. They're built for those, support x86, and are all