add meta files

.gitattributes

@@ -1,34 +1,36 @@
 *.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
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,64 @@
 ---
-#以下为文本生成的 "tasks"示例，您可以从此网页中了解更多相关信息：https://modelscope.cn/docs/%E4%BB%BB%E5%8A%A1%E7%9A%84%E4%BB%8B%E7%BB%8D
-#tasks:
-#- text-generation
-license: Apache License 2.0
+inference: true
+language:
+  - zh
+  - en
+license: other
+model_creator: lmsys
+model_link: https://huggingface.co/lmsys/longchat-13b-16k
+model_name: longchat-13b-16k
+model_type: longchat
+pipeline_tag: text-generation
+quantized_by: shaowenchen
+tasks:
+  - text2text-generation
+tags:
+  - gguf
+  - longchat
+  - 13b
+  - 16k
 ---
-###### 该模型当前使用的是默认介绍模版，处于“预发布”阶段，页面仅限所有者可见。
-###### 请根据[模型贡献文档说明](https://www.modelscope.cn/docs/%E5%A6%82%E4%BD%95%E6%92%B0%E5%86%99%E5%A5%BD%E7%94%A8%E7%9A%84%E6%A8%A1%E5%9E%8B%E5%8D%A1%E7%89%87)，及时完善模型卡片内容。ModelScope平台将在模型卡片完善后展示。谢谢您的理解。
-#### Clone with HTTP
-```bash
- git clone https://www.modelscope.cn/shaowenchen/longchat-13b-16k-gguf.git
-```
+
+## Provided files
+
+| Name                         | Quant method | Size   |
+| ---------------------------- | ------------ | ------ |
+| longchat-13b-16k.Q2_K.gguf   | Q2_K         | 5.1 GB |
+| longchat-13b-16k.Q3_K.gguf   | Q3_K         | 5.9 GB |
+| longchat-13b-16k.Q3_K_L.gguf | Q3_K_L       | 6.5 GB |
+| longchat-13b-16k.Q3_K_S.gguf | Q3_K_S       | 5.3 GB |
+| longchat-13b-16k.Q4_0.gguf   | Q4_0         | 6.9 GB |
+| longchat-13b-16k.Q4_1.gguf   | Q4_1         | 7.6 GB |
+| longchat-13b-16k.Q4_K.gguf   | Q4_K         | 7.3 GB |
+| longchat-13b-16k.Q4_K_S.gguf | Q4_K_S       | 6.9 GB |
+| longchat-13b-16k.Q5_0.gguf   | Q5_0         | 8.4 GB |
+| longchat-13b-16k.Q5_1.gguf   | Q5_1         | 9.1 GB |
+| longchat-13b-16k.Q5_K.gguf   | Q5_K         | 8.6 GB |
+| longchat-13b-16k.Q5_K_S.gguf | Q5_K_S       | 8.4 GB |
+| longchat-13b-16k.Q6_K.gguf   | Q6_K         | 9.9 GB |
+| longchat-13b-16k.Q8_0.gguf   | Q8_0         | 13 GB  |
+| longchat-13b-16k.gguf        | full         | 24 GB  |
+
+Usage:
+
+```
+docker run --rm -it -p 8000:8000 -v /path/to/models:/models -e MODEL=/models/gguf-model-name.gguf hubimage/llama-cpp-python:latest
+```
+
+and you can view http://localhost:8000/docs to see the swagger UI.
+
+## Provided images
+
+| Name                                     | Quant method | Compressed Size |
+| ---------------------------------------- | ------------ | --------------- |
+| `shaowenchen/longchat-13b-16k-gguf:Q2_K` | Q2_K         | 2.88 GB         |
+| `shaowenchen/longchat-13b-16k-gguf:Q3_K` | Q3_K         | 3.3 GB          |
+| `shaowenchen/longchat-13b-16k-gguf:Q4_K` | Q4_K         | 4 GB            |
+
+Usage:
+
+```
+docker run --rm -p 8000:8000 shaowenchen/longchat-13b-16k-gguf:Q2_K
+```
+
+and you can view http://localhost:8000/docs to see the swagger UI.

configuration.json

@@ -0,0 +1,10 @@
+{
+    "framework": "pytorch",
+    "task": "text-generation",
+    "model": {
+        "type": "longchat"
+    },
+    "pipeline": {
+        "type": "longchat-13b-16k-text-generation-pipe"
+    }
+}