Update

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

README.md

@@ -1,11 +1,82 @@
-# Dolphin-2.2-Yi-34B
+---
+base_model: ehartford/dolphin-2_2-yi-34b
+datasets:
+- ehartford/dolphin
+- jondurbin/airoboros-2.2.1
+- ehartford/samantha-data
+- ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
+inference: false
+language:
+- en
+license: other
+license_link: LICENSE
+license_name: yi-license
+model_creator: Eric Hartford
+model_name: Dolphin 2.2 Yi 34B
+model_type: yi
+pipeline_tag: text-generation
+quantized_by: Second State Inc.
+---
 
-## Prompt Template
+<!-- 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 -->
 
-```text
-<|im_start|>system
-{system_message}<|im_end|>
-<|im_start|>user
-{prompt}<|im_end|>
-<|im_start|>assistant
-```
+# Dolphin-2.2-Yi-34B-GGUF
+
+## Original Model
+
+[ehartford/dolphin-2_2-yi-34b](https://huggingface.co/cognitivecomputations/dolphin-2_2-yi-34b)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.2.8](https://github.com/second-state/LlamaEdge/releases/tag/0.2.8) and above
+
+- Prompt template
+
+  - Prompt type: `chatml`
+
+  - Prompt string
+
+    ```text
+    <|im_start|>system
+    {system_message}<|im_end|>
+    <|im_start|>user
+    {prompt}<|im_end|>
+    <|im_start|>assistant
+    ```
+
+  - Reverse prompt: `<|im_end|>`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:dolphin-2.2-yi-34b-ggml-model-q4_0.gguf llama-api-server.wasm -p chatml -r '<|im_end|>'
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:dolphin-2.2-yi-34b-ggml-model-q4_0.gguf llama-chat.wasm -p chatml -r '<|im_end|>' -s 'You are a helpful AI assistant'
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [dolphin-2_2-yi-34b-Q2_K.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q2_K.gguf)     | Q2_K   | 2 | 12.8 GB| smallest, significant quality loss - not recommended for most purposes |
+| [dolphin-2_2-yi-34b-Q3_K_L.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q3_K_L.gguf) | Q3_K_L | 3 | 18.1 GB| small, substantial quality loss |
+| [dolphin-2_2-yi-34b-Q3_K_M.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q3_K_M.gguf) | Q3_K_M | 3 | 16.7 GB| very small, high quality loss |
+| [dolphin-2_2-yi-34b-Q3_K_S.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q3_K_S.gguf) | Q3_K_S | 3 | 15.0 GB| very small, high quality loss |
+| [dolphin-2_2-yi-34b-Q4_0.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q4_0.gguf)     | Q4_0   | 4 | 19.5 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [dolphin-2_2-yi-34b-Q4_K_M.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q4_K_M.gguf) | Q4_K_M | 4 | 20.7 GB| medium, balanced quality - recommended |
+| [dolphin-2_2-yi-34b-Q4_K_S.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q4_K_S.gguf) | Q4_K_S | 4 | 19.6 GB| small, greater quality loss |
+| [dolphin-2_2-yi-34b-Q5_0.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q5_0.gguf)     | Q5_0   | 5 | 23.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [dolphin-2_2-yi-34b-Q5_K_M.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q5_K_M.gguf) | Q5_K_M | 5 | 24.3 GB| large, very low quality loss - recommended |
+| [dolphin-2_2-yi-34b-Q5_K_S.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q5_K_S.gguf) | Q5_K_S | 5 | 23.7 GB| large, low quality loss - recommended |
+| [dolphin-2_2-yi-34b-Q6_K.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q6_K.gguf)     | Q6_K   | 6 | 28.2 GB| very large, extremely low quality loss |
+| [dolphin-2_2-yi-34b-Q8_0.gguf](https://huggingface.co/second-state/Dolphin-2.2-Yi-34B-GGUF/blob/main/dolphin-2_2-yi-34b-Q8_0.gguf)     | Q8_0   | 8 | 36.5 GB| very large, extremely low quality loss - not recommended |