Added New Model & README.md file

Note.txt

@@ -0,0 +1,11 @@
+ret =llm16.export_rkllm(f"orpheus-3b-0.1-ft_{quantized_dtype}_{target_platform}_16bit.rkllm")
+INFO: Setting chat_template to "<|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 04 May 2025\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n[content]<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
+INFO: Setting token_id of bos to 128000
+INFO: Setting token_id of eos to 128009
+INFO: Setting token_id of pad to 128004
+INFO: Setting add_bos_token to True
+Converting model: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 255/255 [00:00<00:00, 1331939.63it/s]
+INFO: Setting max_context_limit to 4096
+INFO: Exporting the model, please wait ....
+[=================================================>] 597/597 (100%)
+INFO: Model has been saved to orpheus_3b_0.1_ft_w8a8_RK3588_16bit.rkllm!

README.md

@@ -0,0 +1,44 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- Prince-1/orpheus_3b_0.1_4bit
+- Prince-1/orpheus_3b_0.1_GGUF
+tags:
+- rkllm
+- text-to-speech
+- tts
+- transformers
+- llama
+---
+
+# Orpheus_3b_0.1_rkllm
+
+**Orpheus_3b_0.1_rkllm** is a [Text-to-Speech](https://huggingface.co/models?pipeline_tag=text-to-speech&sort=trending) model built from Orpheus [16bit](https://huggingface.co/Prince-1/orpheus_3b_0.1_ft_16bit) and [GGUF F16](https://huggingface.co/Prince-1/orpheus_3b_0.1_GGUF), using the [Rkllm-Toolkit](https://github.com/airockchip/rknn-llm).
+
+## Features
+
+- 🎙️ Text-to-Speech capability with optimized inference
+- 🧠 Built from Orpheus 16bit & GGUF F16 formats
+- 🚀 Runs on **RK3588 NPU** using **w8a8 quantization**
+- ⚙️ Powered by [RKLLM Toolkit v1.2.1b1](https://github.com/airockchip/rknn-llm)
+- ⚡ Designed for high-performance on edge devices
+
+## Requirements
+
+- RK3588-based device
+- RKLLM Toolkit v1.2.1b1
+- Compatible runtime environment for deploying quantized models
+
+## Usage
+
+1. Clone or download the model from [Hugging Face](https://huggingface.co/Prince-1/orpheus_3b_0.1_rkllm).
+2. Follow the [RKLLM documentation](https://github.com/airockchip/rknn-llm) to deploy the model.
+3. Use the `rkllm-run` CLI or SDK to perform inference.
+
+
+### License
+This model is released under the **Apache-2.0** license.
+
+---

orpheus_3b_0.1_ft_w8a8_RK3588_16bit.rkllm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e1d03f0c28a98e6112e0760d4714232b0e5dabb3e239c4566e452796ef1355
+size 7596591734

orpheus_3b_0.1_ft_w8a8_RK3588_GGUF_F16.rkllm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e9bfd72d835e935f1c55754deda88103fa05c7704cc6d0bba3278542819401a
+size 7596587782