diff --git a/.gitattributes b/.gitattributes
index 886ac0c..7956351 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1,38 +1,48 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zstandard filter=lfs diff=lfs merge=lfs -text
-*.tfevents* filter=lfs diff=lfs merge=lfs -text
-*.db* filter=lfs diff=lfs merge=lfs -text
-*.ark* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.gguf* filter=lfs diff=lfs merge=lfs -text
-*.ggml filter=lfs diff=lfs merge=lfs -text
-*.llamafile* filter=lfs diff=lfs merge=lfs -text
-*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
diff --git a/Qwen2.5-3B-Instruct-Q2_K.gguf b/Qwen2.5-3B-Instruct-Q2_K.gguf
new file mode 100644
index 0000000..2accfdf
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e18ae976d78da4ed90935fe7c23fdd16fe9101bb5d3fc586ba6453054d43e3a5
+size 1274756000
diff --git a/Qwen2.5-3B-Instruct-Q3_K_L.gguf b/Qwen2.5-3B-Instruct-Q3_K_L.gguf
new file mode 100644
index 0000000..a108535
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c58ac1b9534eeb580ce2a8189dbd1820b4889d710ef986249defda98dcf3a993
+size 1707391904
diff --git a/Qwen2.5-3B-Instruct-Q3_K_M.gguf b/Qwen2.5-3B-Instruct-Q3_K_M.gguf
new file mode 100644
index 0000000..8d5f935
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aad7bf9d708f0ccacb974b54a2c584ecbb2bc07b7f63d5c42e0e469814f0f2d
+size 1590475680
diff --git a/Qwen2.5-3B-Instruct-Q3_K_S.gguf b/Qwen2.5-3B-Instruct-Q3_K_S.gguf
new file mode 100644
index 0000000..bc2fbce
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e5c520e2655555cb77392ee83369e5373e5b421dba8841a2f9449984c2c12f
+size 1454357408
diff --git a/Qwen2.5-3B-Instruct-Q4_0.gguf b/Qwen2.5-3B-Instruct-Q4_0.gguf
new file mode 100644
index 0000000..b0944cc
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ec95864fc1a2023d58c2d77280b6318c1ef29f7bbc0fd459bd2b10998bb3c8
+size 1822849952
diff --git a/Qwen2.5-3B-Instruct-Q4_K_M.gguf b/Qwen2.5-3B-Instruct-Q4_K_M.gguf
new file mode 100644
index 0000000..0526c1c
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef20255e2a9a97b5980fe72ccdc2a90af460754be0e48fec3ad3225044995ea
+size 1929903008
diff --git a/Qwen2.5-3B-Instruct-Q4_K_S.gguf b/Qwen2.5-3B-Instruct-Q4_K_S.gguf
new file mode 100644
index 0000000..26a4961
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5d0a3401311599dda08b128d0541b3ddf2789b04cd1a7d9f2a052da6d698e9
+size 1834384288
diff --git a/Qwen2.5-3B-Instruct-Q5_0.gguf b/Qwen2.5-3B-Instruct-Q5_0.gguf
new file mode 100644
index 0000000..d4f027d
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cacc2a00a02eb8dcdea9513a00c0f6e02898c1b2dff823866c161a31c45eb6bd
+size 2169666464
diff --git a/Qwen2.5-3B-Instruct-Q5_K_M.gguf b/Qwen2.5-3B-Instruct-Q5_K_M.gguf
new file mode 100644
index 0000000..863ec79
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:397ad8b7302b9f7fa11479615ac01f8f82a4a33e16e16618d22eac9b3d557646
+size 2224815008
diff --git a/Qwen2.5-3B-Instruct-Q5_K_S.gguf b/Qwen2.5-3B-Instruct-Q5_K_S.gguf
new file mode 100644
index 0000000..9722174
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377ffd419397fb20f4c1f194c1c8b9a178e1849b2aedf96914d3610db658e16c
+size 2169666464
diff --git a/Qwen2.5-3B-Instruct-Q6_K.gguf b/Qwen2.5-3B-Instruct-Q6_K.gguf
new file mode 100644
index 0000000..a8c8573
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05f445726ce852987659a18f407455268476188e77a0fd57ef99328fe63ad2f
+size 2538159008
diff --git a/Qwen2.5-3B-Instruct-Q8_0.gguf b/Qwen2.5-3B-Instruct-Q8_0.gguf
new file mode 100644
index 0000000..f1969c4
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4420ccb0f1d9e12811d04ae2a28ec881469305f813c62d86c10e595ef8e0111d
+size 3285476256
diff --git a/Qwen2.5-3B-Instruct-f16.gguf b/Qwen2.5-3B-Instruct-f16.gguf
new file mode 100644
index 0000000..d0c401c
--- /dev/null
+++ b/Qwen2.5-3B-Instruct-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfa0216b48c79e4518d5c69ee572eaf8b517892a19048b9e7388fb1442165cdb
+size 6178317216
diff --git a/README.md b/README.md
index ec7ee07..6dfde7d 100644
--- a/README.md
+++ b/README.md
@@ -1,47 +1,87 @@
 ---
-license: Apache License 2.0
-
-#model-type:
-##如 gpt、phi、llama、chatglm、baichuan 等
-#- gpt
-
-#domain:
-##如 nlp、cv、audio、multi-modal
-#- nlp
-
-#language:
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn 
-
-#metrics:
-##如 CIDEr、Blue、ROUGE 等
-#- CIDEr
-
-#tags:
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
-#- pretrained
-
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
+base_model: Qwen/Qwen2.5-3B-Instruct
+license: other
+license_name: qwen-research
+license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSEE
+model_creator: Qwen
+model_name: Qwen2.5-3B-Instruct
+quantized_by: Second State Inc.
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
 ---
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
 
-SDK下载
-```bash
-#安装ModelScope
-pip install modelscope
-```
-```python
-#SDK模型下载
-from modelscope import snapshot_download
-model_dir = snapshot_download('second-state/Qwen2.5-3B-Instruct-GGUF')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/second-state/Qwen2.5-3B-Instruct-GGUF.git
-```
+<!-- 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 -->
 
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
\ No newline at end of file
+# Qwen2.5-3B-Instruct-GGUF
+
+## Original Model
+
+[Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3) 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
+    ```
+
+- Context size: `32000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-3B-Instruct-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --model-name Qwen2.5-3B-Instruct \
+    --prompt-template chatml \
+    --ctx-size 32000
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-3B-Instruct-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template chatml \
+    --ctx-size 32000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Qwen2.5-3B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 676 MB| smallest, significant quality loss - not recommended for most purposes |
+| [Qwen2.5-3B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 880 MB| small, substantial quality loss |
+| [Qwen2.5-3B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 824 MB| very small, high quality loss |
+| [Qwen2.5-3B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 761 MB| very small, high quality loss |
+| [Qwen2.5-3B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 935 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Qwen2.5-3B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 986 MB| medium, balanced quality - recommended |
+| [Qwen2.5-3B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 940 MB| small, greater quality loss |
+| [Qwen2.5-3B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 1.1 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Qwen2.5-3B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 1.13 GB| large, very low quality loss - recommended |
+| [Qwen2.5-3B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 1.1 GB| large, low quality loss - recommended |
+| [Qwen2.5-3B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 1.27 GB| very large, extremely low quality loss |
+| [Qwen2.5-3B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 1.65 GB| very large, extremely low quality loss - not recommended |
+| [Qwen2.5-3B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2.5-3B-Instruct-GGUF/blob/main/Qwen2.5-3B-Instruct-f16.gguf)       | f16    | 16 | 3.09 GB| |
+
+*Quantized with llama.cpp b3751*
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..51b83fb
--- /dev/null
+++ b/config.json
@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..bbeeda1
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
\ No newline at end of file