diff --git a/.gitattributes b/.gitattributes
index 886ac0c..c518ea0 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-Math-7B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-Math-7B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
diff --git a/Qwen2.5-Math-7B-Instruct-Q2_K.gguf b/Qwen2.5-Math-7B-Instruct-Q2_K.gguf
new file mode 100644
index 0000000..d9f2b66
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d4a9e72e7cda9caf429036a25b09d67329f59502ac71c5ca1bd925c1089c0c0
+size 3015940544
diff --git a/Qwen2.5-Math-7B-Instruct-Q3_K_L.gguf b/Qwen2.5-Math-7B-Instruct-Q3_K_L.gguf
new file mode 100644
index 0000000..b5817c7
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:391c20971ca5fe1e31beb0327ecd4e9294afa8bab8c0b3fed73b889b383a389f
+size 4088459712
diff --git a/Qwen2.5-Math-7B-Instruct-Q3_K_M.gguf b/Qwen2.5-Math-7B-Instruct-Q3_K_M.gguf
new file mode 100644
index 0000000..6d8be80
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edcb68501ab9dc84ad239912f49a73917fd3e1d7ee8f332e2bcdc1a1391f6f8b
+size 3808391616
diff --git a/Qwen2.5-Math-7B-Instruct-Q3_K_S.gguf b/Qwen2.5-Math-7B-Instruct-Q3_K_S.gguf
new file mode 100644
index 0000000..a2f71a1
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd934e6279204b16aebfbc51447592abc6fa8cd0b7a82d51eea332ca0925575b
+size 3492368832
diff --git a/Qwen2.5-Math-7B-Instruct-Q4_0.gguf b/Qwen2.5-Math-7B-Instruct-Q4_0.gguf
new file mode 100644
index 0000000..5040636
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6887ebc58cbb91c6aade767d70c9b15283a619693a2d6bcae73cd9d406e4ba
+size 4431391168
diff --git a/Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf b/Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf
new file mode 100644
index 0000000..61fbfae
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fafe6e14252a94d92dbf56408568f79bde5dd7f3d8e7bc0eb6275195c6214d31
+size 4683073984
diff --git a/Qwen2.5-Math-7B-Instruct-Q4_K_S.gguf b/Qwen2.5-Math-7B-Instruct-Q4_K_S.gguf
new file mode 100644
index 0000000..c07f8d9
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d23d98e6516df4e515d12659a41cc4e027e55da91f4ab8390ceba3294bec1fa
+size 4457769408
diff --git a/Qwen2.5-Math-7B-Instruct-Q5_0.gguf b/Qwen2.5-Math-7B-Instruct-Q5_0.gguf
new file mode 100644
index 0000000..f171564
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0820feeb41f8ee15d54c91c472354fe13c8133cdc1587a21327ce19b8f792425
+size 5315176896
diff --git a/Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf b/Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf
new file mode 100644
index 0000000..2f6f0ba
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e593ebd3c758443a7d908882015c6a60ecdb4a965b9d4ac9595712ee7ff28f2
+size 5444831680
diff --git a/Qwen2.5-Math-7B-Instruct-Q5_K_S.gguf b/Qwen2.5-Math-7B-Instruct-Q5_K_S.gguf
new file mode 100644
index 0000000..731f57b
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6359fa7c9a0eb2a1911f3c2d829904a4f3313f7c710860c65daf5b7fc6a6ca
+size 5315176896
diff --git a/Qwen2.5-Math-7B-Instruct-Q6_K.gguf b/Qwen2.5-Math-7B-Instruct-Q6_K.gguf
new file mode 100644
index 0000000..941a1b3
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f8946fb899e3572bd75b6bdd42315a24afc89ac1068323870a0280925baf53
+size 6254199232
diff --git a/Qwen2.5-Math-7B-Instruct-Q8_0.gguf b/Qwen2.5-Math-7B-Instruct-Q8_0.gguf
new file mode 100644
index 0000000..864dba5
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:007b389083750842fc9316a64f54344a9399699305130e735e717a1928d01eeb
+size 8098525632
diff --git a/Qwen2.5-Math-7B-Instruct-f16.gguf b/Qwen2.5-Math-7B-Instruct-f16.gguf
new file mode 100644
index 0000000..88bdba2
--- /dev/null
+++ b/Qwen2.5-Math-7B-Instruct-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff22aaf39c7ac46f5d47dccbcc284ca1036c84aeb121d1e64444137888cedacb
+size 15237853632
diff --git a/README.md b/README.md
index 5f52cd7..c646df3 100644
--- a/README.md
+++ b/README.md
@@ -1,47 +1,105 @@
 ---
-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-Math-7B-Instruct
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct/blob/main/LICENSE
+model_creator: Qwen
+model_name: Qwen2.5-Math-7B-Instruct
+quantized_by: Second State Inc.
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- code
+- codeqwen
+- chat
+- qwen
+- qwen-coder
 ---
-### 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-Math-7B-Instruct-GGUF')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/second-state/Qwen2.5-Math-7B-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-Math-7B-Instruct-GGUF
+
+## Original Model
+
+[Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: coming soon
+
+<!-- - LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3) -->
+
+<!-- - Prompt template
+
+  - Prompt type: `qwen-2.5-coder`
+
+  - Prompt string
+ 
+    - File-Level Code Completion (Fill in the middle)
+
+      ```text
+      <|fim_prefix|>{prefix_code}<|fim_suffix|>{suffix_code}<|fim_middle|>
+      ```
+ 
+      *Reference: https://github.com/QwenLM/Qwen2.5-Coder?tab=readme-ov-file#3-file-level-code-completion-fill-in-the-middle*
+
+    - Repository-Level Code Completion
+   
+      ```text
+      <|repo_name|>{repo_name}
+      <|file_sep|>{file_path1} 
+      {file_content1}
+      <|file_sep|>{file_path2} 
+      {file_content2}
+      ```
+
+      *Reference: https://github.com/QwenLM/Qwen2.5-Coder?tab=readme-ov-file#4-repository-level-code-completion*
+
+- Context size: `128000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --model-name Qwen2.5-Math-7B-Instruct \
+    --prompt-template qwen-2.5-coder \
+    --ctx-size 128000
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template qwen-2.5-coder \
+    --ctx-size 128000
+  ``` -->
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Qwen2.5-Math-7B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 3.02 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Qwen2.5-Math-7B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.09 GB| small, substantial quality loss |
+| [Qwen2.5-Math-7B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 3.81 GB| very small, high quality loss |
+| [Qwen2.5-Math-7B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.49 GB| very small, high quality loss |
+| [Qwen2.5-Math-7B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 4.43 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.68 GB| medium, balanced quality - recommended |
+| [Qwen2.5-Math-7B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.46 GB| small, greater quality loss |
+| [Qwen2.5-Math-7B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 5.32 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.44 GB| large, very low quality loss - recommended |
+| [Qwen2.5-Math-7B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.32 GB| large, low quality loss - recommended |
+| [Qwen2.5-Math-7B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 6.25 GB| very large, extremely low quality loss |
+| [Qwen2.5-Math-7B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 8.21 GB| very large, extremely low quality loss - not recommended |
+| [Qwen2.5-Math-7B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2.5-Math-7B-Instruct-GGUF/blob/main/Qwen2.5-Math-7B-Instruct-f16.gguf)       | f16    | 16 | 15.2 GB| |
+
+*Quantized with llama.cpp b3751*
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..742831f
--- /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": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 4096,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
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