diff --git a/.gitattributes b/.gitattributes
index 11a9c76..a69016b 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1,39 +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
-*.gguf filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
diff --git a/Llama-3.2-1B-Instruct-Q2_K.gguf b/Llama-3.2-1B-Instruct-Q2_K.gguf
new file mode 100644
index 0000000..48146d6
--- /dev/null
+++ b/Llama-3.2-1B-Instruct-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cbccffcba1e679d2fb906a55b5d6d641aa21bff9ee20fe30cef6dd6b9f8e410
+size 580874080
diff --git a/Llama-3.2-1B-Instruct-Q3_K_L.gguf b/Llama-3.2-1B-Instruct-Q3_K_L.gguf
new file mode 100644
index 0000000..8ed6e18
--- /dev/null
+++ b/Llama-3.2-1B-Instruct-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e89a46e80c150f92bc0d5dfacb069f46770807664340339a22d886031ee06ddc
+size 732524384
diff --git a/Llama-3.2-1B-Instruct-Q3_K_M.gguf b/Llama-3.2-1B-Instruct-Q3_K_M.gguf
new file mode 100644
index 0000000..9ed912c
--- /dev/null
+++ b/Llama-3.2-1B-Instruct-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdd2550b78bdee5653da8f9d07d74faaafd7cc50602eac9107d8f2c60677d24
+size 690843488
diff --git a/Llama-3.2-1B-Instruct-Q3_K_S.gguf b/Llama-3.2-1B-Instruct-Q3_K_S.gguf
new file mode 100644
index 0000000..dd8a14d
--- /dev/null
+++ b/Llama-3.2-1B-Instruct-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5363d4847936b37950b1d048199b616b80edd40e78ed15e7b0f2e36c32433b
+size 641691488
diff --git a/Llama-3.2-1B-Instruct-Q4_K_M.gguf b/Llama-3.2-1B-Instruct-Q4_K_M.gguf
new file mode 100644
index 0000000..eb8accb
--- /dev/null
+++ b/Llama-3.2-1B-Instruct-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95df2f5144fd67bf11421ad59812fbde45a79c90eb49cb5d79e3d7bddaa1331
+size 807694176
diff --git a/Llama-3.2-1B-Instruct-Q4_K_S.gguf b/Llama-3.2-1B-Instruct-Q4_K_S.gguf
new file mode 100644
index 0000000..c63fc51
--- /dev/null
+++ b/Llama-3.2-1B-Instruct-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e256d51eed0799552f91a4fb8f0d05315b3e3dc1cd4499514e7d87a845951c88
+size 775647072
diff --git a/Llama-3.2-1B-Instruct-Q5_0.gguf b/Llama-3.2-1B-Instruct-Q5_0.gguf
new file mode 100644
index 0000000..035e17f
--- /dev/null
+++ b/Llama-3.2-1B-Instruct-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:922306ce6b89b731d20130c2a5e909be530c5703fd24b26f7d050bad3faf3fc5
+size 892563296
diff --git a/Llama-3.2-1B-Instruct-Q5_K_M.gguf b/Llama-3.2-1B-Instruct-Q5_K_M.gguf
new file mode 100644
index 0000000..f3d855b
--- /dev/null
+++ b/Llama-3.2-1B-Instruct-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd16584b15af8c268ca60454b63b5021b0b2c7edf66cff2b41210a333b2233d
+size 911503200
diff --git a/Llama-3.2-1B-Instruct-Q5_K_S.gguf b/Llama-3.2-1B-Instruct-Q5_K_S.gguf
new file mode 100644
index 0000000..49de768
--- /dev/null
+++ b/Llama-3.2-1B-Instruct-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66260aca245c04327590457d52debf378e0fc93b881b2effb71f9a00703a1953
+size 892563296
diff --git a/Llama-3.2-1B-Instruct-Q6_K.gguf b/Llama-3.2-1B-Instruct-Q6_K.gguf
new file mode 100644
index 0000000..beb192e
--- /dev/null
+++ b/Llama-3.2-1B-Instruct-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe00ecc20650188a714bf1766cecbd938e6119e9311c8fe91ca3fb5f3246591
+size 1021800288
diff --git a/Llama-3.2-1B-Instruct-f16.gguf b/Llama-3.2-1B-Instruct-f16.gguf
new file mode 100644
index 0000000..75e2bb8
--- /dev/null
+++ b/Llama-3.2-1B-Instruct-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f33ad43d2b85b908ff06fe7002b69806a57359b9b2617ca27d7bdea428ae146
+size 2479595360
diff --git a/README.md b/README.md
index 0589e3a..e6f0488 100644
--- a/README.md
+++ b/README.md
@@ -1,51 +1,99 @@
----
-frameworks:
-- other
-license: Apache License 2.0
-tasks:
-- text-generation
-
-#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
----
-### 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/Llama-3.2-1B-Instruct-GGUF')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/second-state/Llama-3.2-1B-Instruct-GGUF.git
-```
-
-<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
+---
+base_model: meta-llama/Llama-3.2-1B-Instruct
+license: llama3.2
+model_creator: meta
+model_name: Llama-3.2-1B-Instruct
+quantized_by: Second State Inc.
+language:
+- en
+- de
+- fr
+- it
+- pt
+- hi
+- es
+- th
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- chat
+- llama
+- llama-3
+---
+
+<!-- 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 -->
+
+# Llama-3.2-1B-Instruct-GGUF
+
+## Original Model
+
+[meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.14.5](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.5) 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
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-1B-Instruct-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template llama-3-chat \
+      --ctx-size 128000 \
+      --model-name Llama-3.2-1b
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-1B-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 |
+| ---- | ---- | ---- | ---- | ----- |
+| [Llama-3.2-1B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 581 MB| smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3.2-1B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 733 MB| small, substantial quality loss |
+| [Llama-3.2-1B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 691 MB| very small, high quality loss |
+| [Llama-3.2-1B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 642 MB| very small, high quality loss |
+| [Llama-3.2-1B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 771 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3.2-1B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 808 MB| medium, balanced quality - recommended |
+| [Llama-3.2-1B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 776 MB| small, greater quality loss |
+| [Llama-3.2-1B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 893 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3.2-1B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 912 MB| large, very low quality loss - recommended |
+| [Llama-3.2-1B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 893 MB| large, low quality loss - recommended |
+| [Llama-3.2-1B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 1.02 GB| very large, extremely low quality loss |
+| [Llama-3.2-1B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 1.32 GB| very large, extremely low quality loss - not recommended |
+| [Llama-3.2-1B-Instruct-f16.gguf](https://huggingface.co/second-state/Llama-3.2-1B-Instruct-GGUF/blob/main/Llama-3.2-1B-Instruct-f16.gguf)       | f16    | 16 | 2.48 GB| |
+
+*Quantized with llama.cpp b3807*
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..3e3aaf5
--- /dev/null
+++ b/config.json
@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}