diff --git a/.gitattributes b/.gitattributes
index 886ac0c..4517c75 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
+internlm2_5-20b-chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-f16.gguf filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
index 596c495..6dd6c59 100644
--- a/README.md
+++ b/README.md
@@ -1,47 +1,94 @@
----
-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
----
-### 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/internlm2_5-20b-chat-GGUF')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/second-state/internlm2_5-20b-chat-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
+---
+license: other
+pipeline_tag: text-generation
+base_model: internlm/internlm2_5-20b-chat
+model_creator: InternLM
+model_name: internlm2_5-20b-chat
+quantized_by: Second State Inc.
+---
+
+<!-- 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 -->
+
+# internlm2_5-20b-chat-GGUF
+
+## Original Model
+
+[internlm/internlm2_5-20b-chat](https://huggingface.co/internlm/internlm2_5-20b-chat)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.13.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.13.0) 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
+
+  - Chat
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:internlm2_5-20b-chat-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template chatml \
+      --ctx-size 32000 \
+      --model-name internlm2_5-20b-chat
+    ```
+
+  - Tool use
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:internlm2_5-20b-chat-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template internlm-2-tool \
+      --ctx-size 32000 \
+      --model-name internlm2_5-20b-chat
+    ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. \
+    --nn-preload default:GGML:AUTO:internlm2_5-20b-chat-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template chatml \
+    --ctx-size 32000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [internlm2_5-20b-chat-Q2_K.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q2_K.gguf)     | Q2_K   | 2 | 7.55 GB| smallest, significant quality loss - not recommended for most purposes |
+| [internlm2_5-20b-chat-Q3_K_L.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q3_K_L.gguf) | Q3_K_L | 3 | 10.6 GB| small, substantial quality loss |
+| [internlm2_5-20b-chat-Q3_K_M.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q3_K_M.gguf) | Q3_K_M | 3 | 9.72 GB| very small, high quality loss |
+| [internlm2_5-20b-chat-Q3_K_S.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q3_K_S.gguf) | Q3_K_S | 3 | 8.76 GB| very small, high quality loss |
+| [internlm2_5-20b-chat-Q4_0.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q4_0.gguf)     | Q4_0   | 4 | 11.3 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [internlm2_5-20b-chat-Q4_K_M.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q4_K_M.gguf) | Q4_K_M | 4 | 12.0 GB| medium, balanced quality - recommended |
+| [internlm2_5-20b-chat-Q4_K_S.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q4_K_S.gguf) | Q4_K_S | 4 | 11.4 GB| small, greater quality loss |
+| [internlm2_5-20b-chat-Q5_0.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q5_0.gguf)     | Q5_0   | 5 | 13.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [internlm2_5-20b-chat-Q5_K_M.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q5_K_M.gguf) | Q5_K_M | 5 | 14.1 GB| large, very low quality loss - recommended |
+| [internlm2_5-20b-chat-Q5_K_S.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q5_K_S.gguf) | Q5_K_S | 5 | 13.7 GB| large, low quality loss - recommended |
+| [internlm2_5-20b-chat-Q6_K.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q6_K.gguf)     | Q6_K   | 6 | 16.3 GB| very large, extremely low quality loss |
+| [internlm2_5-20b-chat-Q8_0.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q8_0.gguf)     | Q8_0   | 8 | 21.1 GB| very large, extremely low quality loss - not recommended |
+| [internlm2_5-20b-chat-f16.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-f16.gguf)       | f16    | 16 | 39.7 GB|  |
+
+*Quantized with llama.cpp b3499*
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..9ee79ca
--- /dev/null
+++ b/config.json
@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "InternLM2ForCausalLM"
+  ],
+  "attn_implementation": "eager",
+  "auto_map": {
+    "AutoConfig": "configuration_internlm2.InternLM2Config",
+    "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
+    "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
+    "AutoModelForSequenceClassification": "modeling_internlm2.InternLM2ForSequenceClassification"
+  },
+  "bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 32768,
+  "model_type": "internlm2",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "type": "dynamic",
+    "factor": 2.5
+  },
+  "rope_theta": 50000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 92544
+}
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
diff --git a/internlm2_5-20b-chat-Q2_K.gguf b/internlm2_5-20b-chat-Q2_K.gguf
new file mode 100644
index 0000000..49b3e81
--- /dev/null
+++ b/internlm2_5-20b-chat-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e865a42a55067b976d88b3c049e454e21e03bcd3d6b85077b34f5e956dc03974
+size 7546670592
diff --git a/internlm2_5-20b-chat-Q3_K_L.gguf b/internlm2_5-20b-chat-Q3_K_L.gguf
new file mode 100644
index 0000000..44a0703
--- /dev/null
+++ b/internlm2_5-20b-chat-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff45b608bffaffb01a02673c5c0fec9d346e0c73606ad3ad0270564290a1005
+size 10551178752
diff --git a/internlm2_5-20b-chat-Q3_K_M.gguf b/internlm2_5-20b-chat-Q3_K_M.gguf
new file mode 100644
index 0000000..f4bf6d6
--- /dev/null
+++ b/internlm2_5-20b-chat-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7fdc6ce5941c3172610ccbe6f473ccba135ad70b0caaa1e5ff972c16cd056c
+size 9722279424
diff --git a/internlm2_5-20b-chat-Q3_K_S.gguf b/internlm2_5-20b-chat-Q3_K_S.gguf
new file mode 100644
index 0000000..d90aeaa
--- /dev/null
+++ b/internlm2_5-20b-chat-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb16d145afbcc1f2527962deb50079145d2d281e780dab0c7f359535bb6b3ff
+size 8760473088
diff --git a/internlm2_5-20b-chat-Q4_0.gguf b/internlm2_5-20b-chat-Q4_0.gguf
new file mode 100644
index 0000000..952cdbc
--- /dev/null
+++ b/internlm2_5-20b-chat-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4ee7370c1edfda367911d771ba28a0286072aec8ba4e9b70f89f8e0d5f9be3
+size 11322686976
diff --git a/internlm2_5-20b-chat-Q4_K_M.gguf b/internlm2_5-20b-chat-Q4_K_M.gguf
new file mode 100644
index 0000000..43fa734
--- /dev/null
+++ b/internlm2_5-20b-chat-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc904dbbb9e18494961f7553ab0069a6fd4e4f9a35c3799e83163d79c654ecf0
+size 11984469504
diff --git a/internlm2_5-20b-chat-Q4_K_S.gguf b/internlm2_5-20b-chat-Q4_K_S.gguf
new file mode 100644
index 0000000..6f24ba6
--- /dev/null
+++ b/internlm2_5-20b-chat-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a40f2b746a2440162a9b45328bc08b57dcc1d6e1db86c8e7a291cc628f7558e
+size 11401330176
diff --git a/internlm2_5-20b-chat-Q5_0.gguf b/internlm2_5-20b-chat-Q5_0.gguf
new file mode 100644
index 0000000..3340697
--- /dev/null
+++ b/internlm2_5-20b-chat-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d194531c55962c761ab768fdbcb69d251435325d361b05577c818d9f2fbb1a74
+size 13734182400
diff --git a/internlm2_5-20b-chat-Q5_K_M.gguf b/internlm2_5-20b-chat-Q5_K_M.gguf
new file mode 100644
index 0000000..9cc204f
--- /dev/null
+++ b/internlm2_5-20b-chat-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5504320cb5ffede2d807ed15b93278095a27a5a959285fa22d803bd08a0784a1
+size 14075100672
diff --git a/internlm2_5-20b-chat-Q5_K_S.gguf b/internlm2_5-20b-chat-Q5_K_S.gguf
new file mode 100644
index 0000000..134bf41
--- /dev/null
+++ b/internlm2_5-20b-chat-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f380a21b71722138600e414c382cee137ce8096cb0e1079f110e7e94e1c211e
+size 13734182400
diff --git a/internlm2_5-20b-chat-Q6_K.gguf b/internlm2_5-20b-chat-Q6_K.gguf
new file mode 100644
index 0000000..cbf97b6
--- /dev/null
+++ b/internlm2_5-20b-chat-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9082b5af0c7daf349ae5556657bb5f6797bf5bd459ed58906d7f75a0ffed35d0
+size 16296396288
diff --git a/internlm2_5-20b-chat-Q8_0.gguf b/internlm2_5-20b-chat-Q8_0.gguf
new file mode 100644
index 0000000..551f8b8
--- /dev/null
+++ b/internlm2_5-20b-chat-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7537641d60a4c944a3d564bdc0134cd9f9df6315e55b761ea19df44db0743c
+size 21106374144
diff --git a/internlm2_5-20b-chat-f16.gguf b/internlm2_5-20b-chat-f16.gguf
new file mode 100644
index 0000000..5159beb
--- /dev/null
+++ b/internlm2_5-20b-chat-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2890d59c2e17f2d42e9a0e9e538c6349a69f1b387eb4f87900545d86a5313c8
+size 39725643264