Add

Signed-off-by: Xin Liu <sam@secondstate.io>

README.md

@@ -1,13 +1,78 @@
+---
+base_model: microsoft/Orca-2-13b
+inference: false
+library_name: transformers
+license: other
+license_name: microsoft-research-license
+license_link: LICENSE
+model_creator: TinyLlama
+model_name: Tinyllama 1.1B Chat v1.0
+model_type: tinyllama
+tags:
+- orca
+- orca2
+- microsoft
+pipeline_tag: text-generation
+quantized_by: Second State Inc.
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/second-state/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
 # Orca-2-13B-GGUF
 
-The original model is [Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b).
+## Original Model
+
+[microsoft/Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.2.4](https://github.com/second-state/LlamaEdge/releases/tag/0.2.4)
+
+- Prompt template
+
+  - Prompt type: `chatml`
+
+  - Prompt string
+
+    ```text
+    <|im_start|>system
+    {system_message}<|im_end|>
+    <|im_start|>user
+    {prompt}<|im_end|>
+    <|im_start|>assistant
+    ```
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Orca-2-13b-Q5_K_M.gguf llama-api-server.wasm -p chatml
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Orca-2-13b-Q5_K_M.gguf llama-chat.wasm -p chatml
+  ```
 
-## Prompt Template
+## Quantized GGUF Models
 
-```text
-<|im_start|>system
-{system_message}<|im_end|>
-<|im_start|>user
-{prompt}<|im_end|>
-<|im_start|>assistant
-```
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Orca-2-13b-Q2_K.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q2_K.gguf)     | Q2_K   | 2 | 5.43 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Orca-2-13b-Q3_K_L.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| small, substantial quality loss |
+| [Orca-2-13b-Q3_K_M.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| very small, high quality loss |
+| [Orca-2-13b-Q3_K_S.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| very small, high quality loss |
+| [Orca-2-13b-Q4_0.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q4_0.gguf)     | Q4_0   | 4 | 7.37 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Orca-2-13b-Q4_K_M.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| medium, balanced quality - recommended |
+| [Orca-2-13b-Q4_K_S.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| small, greater quality loss |
+| [Orca-2-13b-Q5_0.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q5_0.gguf)     | Q5_0   | 5 | 8.97 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Orca-2-13b-Q5_K_M.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| large, very low quality loss - recommended |
+| [Orca-2-13b-Q5_K_S.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| large, low quality loss - recommended |
+| [Orca-2-13b-Q6_K.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q6_K.gguf)     | Q6_K   | 6 | 10.7 GB| very large, extremely low quality loss |
+| [Orca-2-13b-Q8_0.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q8_0.gguf)     | Q8_0   | 8 | 13.8 GB| very large, extremely low quality loss - not recommended |