diff --git a/.gitattributes b/.gitattributes
index 886ac0c..b7722c6 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
+Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3.1-8B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
diff --git a/Meta-Llama-3.1-8B-Instruct-Q2_K.gguf b/Meta-Llama-3.1-8B-Instruct-Q2_K.gguf
new file mode 100644
index 0000000..ab4c41a
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978c23cad76854c8bf944a819159697215575a72a8d70910b41e9effbd7badfb
+size 3179131552
diff --git a/Meta-Llama-3.1-8B-Instruct-Q3_K_L.gguf b/Meta-Llama-3.1-8B-Instruct-Q3_K_L.gguf
new file mode 100644
index 0000000..d59fa31
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46bb86256326b4fea38c4adf8bd70b4e0ad5551db43ef9fe0e5489411ca0dc1f
+size 4321956512
diff --git a/Meta-Llama-3.1-8B-Instruct-Q3_K_M.gguf b/Meta-Llama-3.1-8B-Instruct-Q3_K_M.gguf
new file mode 100644
index 0000000..7c9f1d2
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1577fefd7a7d843f89b25d32849e3fa2e19a5373e620bce504d2dbc57b73f1cf
+size 4018918048
diff --git a/Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf b/Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf
new file mode 100644
index 0000000..f553f2a
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74d716226d30c2516d26bbd4cff01f951433bfe717e1ef4b61899fbaf7a8152
+size 3664499360
diff --git a/Meta-Llama-3.1-8B-Instruct-Q4_0.gguf b/Meta-Llama-3.1-8B-Instruct-Q4_0.gguf
new file mode 100644
index 0000000..5b6ba96
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323f9cc1282b3d5bb817a0af2f3cfd0a6a68496d02ae6d420f5b14ed688ceb3f
+size 4661211808
diff --git a/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf b/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf
new file mode 100644
index 0000000..e217dc7
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415df20ac06158f3b473bf6ea3aa666e052ed55e6e6ff6b0dbb9db7af4180d36
+size 4920734368
diff --git a/Meta-Llama-3.1-8B-Instruct-Q4_K_S.gguf b/Meta-Llama-3.1-8B-Instruct-Q4_K_S.gguf
new file mode 100644
index 0000000..aa0fc38
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a8ba1673c3e6fdca8397a8abd35af58cde851e471c30fc4a621f80274f3f92
+size 4692669088
diff --git a/Meta-Llama-3.1-8B-Instruct-Q5_0.gguf b/Meta-Llama-3.1-8B-Instruct-Q5_0.gguf
new file mode 100644
index 0000000..0100c82
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b053deabe91246648fabf95b972d6a64e4077e432a288a50629aefe2fcfa719
+size 5599294112
diff --git a/Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf b/Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf
new file mode 100644
index 0000000..3a9b901
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e75ee4ff8356eb25ad9f5055cf527e7d2654c005dde8fb5481db50e5164e0f
+size 5732987552
diff --git a/Meta-Llama-3.1-8B-Instruct-Q5_K_S.gguf b/Meta-Llama-3.1-8B-Instruct-Q5_K_S.gguf
new file mode 100644
index 0000000..998a13d
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a6be00c21161cf45c1f0172a0fdbf4a24f1cb58c84593c66c2db74527de2b3
+size 5599294112
diff --git a/Meta-Llama-3.1-8B-Instruct-Q6_K.gguf b/Meta-Llama-3.1-8B-Instruct-Q6_K.gguf
new file mode 100644
index 0000000..327cfa8
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b49f782d79e5d33b203c5fca60140586ae3abeec80b894bf8db40f594786ece
+size 6596006560
diff --git a/Meta-Llama-3.1-8B-Instruct-Q8_0.gguf b/Meta-Llama-3.1-8B-Instruct-Q8_0.gguf
new file mode 100644
index 0000000..63e9446
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91818e082e2d87acf79032cb0c9d8e4e4878b1ee38ba68f09e120d47b3aeb04c
+size 8540770976
diff --git a/Meta-Llama-3.1-8B-Instruct-f16.gguf b/Meta-Llama-3.1-8B-Instruct-f16.gguf
new file mode 100644
index 0000000..38ec6cd
--- /dev/null
+++ b/Meta-Llama-3.1-8B-Instruct-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ff778433e6590189788b54c00aba834d6eb167808ec32ae659964392a07230
+size 16068891296
diff --git a/README.md b/README.md
index 08c3198..4f4239b 100644
--- a/README.md
+++ b/README.md
@@ -1,47 +1,115 @@
 ---
-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
+license: llama3.1
+model_name: Meta-Llama-3.1-8B-Instruct-GGUF
+arxiv: 2307.09288
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct-GGUF
+inference: false
+model_creator: Meta Llama3
+model_type: llama
+pipeline_tag: text-generation
+quantized_by: Second State Inc.
+language:
+- en
+- de
+- fr
+- it
+- pt
+- hi
+- es
+- th
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-3
 ---
-### 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/Meta-Llama-3.1-8B-Instruct-GGUF')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/second-state/Meta-Llama-3.1-8B-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
+# Meta-Llama-3.1-8B-Instruct-GGUF
+
+## Original Model
+
+[meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.12.4](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.4) and above
+
+- Prompt template
+
+  - Prompt type: `llama-3-chat`
+
+  - Prompt string
+
+    ```text
+    <|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+    {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+    {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+    {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+    {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+    ```
+
+- Context size: `128000`
+
+- Run as LlamaEdge service
+
+  - Chat
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template llama-3-chat \
+      --ctx-size 128000 \
+      --model-name Llama-3.1-8b
+    ```
+
+  - Tool use
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template llama-3-tool \
+      --ctx-size 128000 \
+      --model-name Llama-3.1-8b
+    ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template llama-3-chat \
+    --ctx-size 128000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Meta-Llama-3.1-8B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Meta-Llama-3.1-8B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
+| [Meta-Llama-3.1-8B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
+| [Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
+| [Meta-Llama-3.1-8B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
+| [Meta-Llama-3.1-8B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
+| [Meta-Llama-3.1-8B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
+| [Meta-Llama-3.1-8B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
+| [Meta-Llama-3.1-8B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 6.6 GB| very large, extremely low quality loss |
+| [Meta-Llama-3.1-8B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
+| [Meta-Llama-3.1-8B-Instruct-f16.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/Meta-Llama-3.1-8B-Instruct-f16.gguf)       | f16    | 16 | 16.1 GB|  |
+
+*Quantized with llama.cpp b3445.*
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..0bb6fd7
--- /dev/null
+++ b/config.json
@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "low_freq_factor": 1.0,
+    "high_freq_factor": 4.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}
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