初始化项目，由ModelHub XC社区提供模型

Model: shaowenchen/chinese-llama-2-13b-16k-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +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
+*.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
+*.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

@@ -0,0 +1,48 @@
+---
+inference: false
+language:
+  - zh
+license: other
+model_creator: ziqingyang
+model_link: https://huggingface.co/ziqingyang/chinese-llama-2-13b-16k
+model_name: chinese-llama-2-13b-16k
+model_type: llama
+pipeline_tag: text-generation
+quantized_by: shaowenchen
+tasks:
+  - text2text-generation
+tags:
+  - meta
+  - gguf
+  - llama
+  - llama-2
+  - chinese
+---
+
+## Provided files
+
+| Name                                | Quant method | Size  |
+| ----------------------------------- | ------------ | ----- |
+| chinese-llama-2-13b-16k.Q2_K.gguf   | Q2_K         | 5.2 G |
+| chinese-llama-2-13b-16k.Q3_K.gguf   | Q3_K         | 6.0 G |
+| chinese-llama-2-13b-16k.Q3_K_L.gguf | Q3_K_L       | 6.6 G |
+| chinese-llama-2-13b-16k.Q3_K_S.gguf | Q3_K_S       | 5.4 G |
+| chinese-llama-2-13b-16k.Q4_0.gguf   | Q4_0         | 7.0 G |
+| chinese-llama-2-13b-16k.Q4_1.gguf   | Q4_1         | 7.8 G |
+| chinese-llama-2-13b-16k.Q4_K.gguf   | Q4_K         | 7.5 G |
+| chinese-llama-2-13b-16k.Q4_K_S.gguf | Q4_K_S       | 7.1 G |
+| chinese-llama-2-13b-16k.Q5_0.gguf   | Q5_0         | 8.5 G |
+| chinese-llama-2-13b-16k.Q5_1.gguf   | Q5_1         | 9.3 G |
+| chinese-llama-2-13b-16k.Q5_K.gguf   | Q5_K         | 8.8 G |
+| chinese-llama-2-13b-16k.Q5_K_S.gguf | Q5_K_S       | 8.5 G |
+| chinese-llama-2-13b-16k.Q6_K.gguf   | Q6_K         | 10 G  |
+| chinese-llama-2-13b-16k.Q8_0.gguf   | Q8_0         | 13 G  |
+| chinese-llama-2-13b-16k.gguf        | full         | 25 G  |
+
+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.

chinese-llama-2-13b-16k.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c2e4ff8f718ff224fccb78f9029da59260c15d07a6d446ea8905fd0304d0376
+size 5566836448

chinese-llama-2-13b-16k.Q3_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae530c01789d6aaca0a558c0784f49bf9ca602d7a242ac3dddeddcaa4b41698f
+size 6487371488

chinese-llama-2-13b-16k.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e0efdab01aaf08cdd7dbf50c7f9d83175f8b668657318bea10a99b5f14acdc
+size 7079161568

chinese-llama-2-13b-16k.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb55c41d1156b48ac595a37b7c7ad0f32470d7dcf4132f8f201587eb934abdbc
+size 5808582368

chinese-llama-2-13b-16k.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e66d1f368c9ee5a0054c9b3b69da3fd88b2a47df235c637568771b1a4a3573
+size 7531278048

chinese-llama-2-13b-16k.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc61788ee5336f4bc347962ea6da530f0e80e9c14d75fa02aac6940ca238c8c0
+size 8341958368

chinese-llama-2-13b-16k.Q4_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624222a7e94bac008ea1fb1fe014bb892b689b2d36cff45a1b0af78620dfa45c
+size 8031399648

chinese-llama-2-13b-16k.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57eb97324968dd7a9a3d17d641be688788af47b45d2a05f98566673e487158b
+size 7579774688

chinese-llama-2-13b-16k.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55af75d7e5038e8b26b30559199f93a56457d4b693282f1a68a04ea17c6327e
+size 9152638688

chinese-llama-2-13b-16k.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e738b7ec39af0ed3cbb44c57857789c551754530c90821a1c1f564fd2da2b7
+size 9963319008

chinese-llama-2-13b-16k.Q5_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3117593333dd8cb14dec1232511b454a923de3b0746ef8ab75ae43be5dc09d2
+size 9410277088

chinese-llama-2-13b-16k.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46d551e87441c368dd030ed3fcd749aa12a4f725630760292ff46e42246fa9dd
+size 9152638688

chinese-llama-2-13b-16k.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e9993e3b86f070f04b4d62f9506fae27d013651d38a7ba85e4c3791c6b51d9
+size 10875334368

chinese-llama-2-13b-16k.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf1487e8bf9188418649530afd4f906fb0880292ba284c21ee83ccab461c39d
+size 14085287648

chinese-llama-2-13b-16k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50541e3dab4904a9bc6e18884c94ef72f8c8c54adbc73a58336507ca10388eba
+size 26510913216

configuration.json

@@ -0,0 +1,10 @@
+{
+    "framework": "pytorch",
+    "task": "text-generation",
+    "model": {
+        "type": "llama2"
+    },
+    "pipeline": {
+        "type": "chinese-llama-2-13b-16k-text-generation-pipe"
+    }
+}