Update

Signed-off-by: Xin Liu <[email protected]>

README.md

@@ -1,3 +1,59 @@
 ---
+base_model: nomic-ai/nomic-embed-text-v1.5
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
 license: apache-2.0
+model_creator: nomic-ai
+quantized_by: Second State Inc.
+language: en
 ---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/LlamaEdge/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 -->
+
+# Nomic-embed-text-v1.5-Embedding-GGUF
+
+## Original Model
+
+[nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.8.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.2) and above
+
+- Context size: `768`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:nomic-embed-text-v1.5-f16.gguf \
+    llama-api-server.wasm \
+    --prompt-template llama-2-chat \
+    --ctx-size 768 \
+    --model-name nomic-embed-text-v1.5
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [nomic-embed-text-v1.5-Q2_K.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q2_K.gguf)     | Q2_K   | 2 |60.9 MB| smallest, significant quality loss - not recommended for most purposes |
+| [nomic-embed-text-v1.5-Q3_K_L.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q3_K_L.gguf) | Q3_K_L | 3 | 80.7 MB| small, substantial quality loss |
+| [nomic-embed-text-v1.5-Q3_K_M.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q3_K_M.gguf) | Q3_K_M | 3 | 76.3 MB| very small, high quality loss |
+| [nomic-embed-text-v1.5-Q3_K_S.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q3_K_S.gguf) | Q3_K_S | 3 | 68.8 MB| very small, high quality loss |
+| [nomic-embed-text-v1.5-Q4_0.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q4_0.gguf)     | Q4_0   | 4 | 84.8 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [nomic-embed-text-v1.5-Q4_K_M.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q4_K_M.gguf) | Q4_K_M | 4 | 90.2 MB| medium, balanced quality - recommended |
+| [nomic-embed-text-v1.5-Q4_K_S.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q4_K_S.gguf) | Q4_K_S | 4 | 84.1 MB| small, greater quality loss |
+| [nomic-embed-text-v1.5-Q5_0.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q5_0.gguf)     | Q5_0   | 5 | 98 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [nomic-embed-text-v1.5-Q5_K_M.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q5_K_M.gguf) | Q5_K_M | 5 | 103 MB| large, very low quality loss - recommended |
+| [nomic-embed-text-v1.5-Q5_K_S.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q5_K_S.gguf) | Q5_K_S | 5 | 98 MB| large, low quality loss - recommended |
+| [nomic-embed-text-v1.5-Q6_K.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q6_K.gguf)     | Q6_K   | 6 | 113 MB| very large, extremely low quality loss |
+| [nomic-embed-text-v1.5-Q8_0.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-Q8_0.gguf)     | Q8_0   | 8 | 146 MB| very large, extremely low quality loss - not recommended |
+| [nomic-embed-text-v1.5-f16.gguf](https://huggingface.co/second-state/Nomic-embed-text-v1.5-GGUF/blob/main/nomic-embed-text-v1.5-f16.gguf)     | Q8_0   | 8 | 274 MB| very large, extremely low quality loss - not recommended |
+
+*Quantized with llama.cpp b2636*