From 670dcf5c6bf3453924016c3759c08b6e0dde8ed6 Mon Sep 17 00:00:00 2001 From: ai-modelscope Date: Mon, 28 Oct 2024 15:40:35 +0800 Subject: [PATCH] Update README.md with license information (#1) - Update README.md with license information (22f8e64fa95921df1603b2482a486dc4292ddc4f) Co-authored-by: Chen_01AI --- .gitattributes | 38 ++++++---- README.md | 126 ++++++++++++++++++++++----------- Yi-1.5-9B-Chat-16K-Q2_K.gguf | 3 + Yi-1.5-9B-Chat-16K-Q3_K_L.gguf | 3 + Yi-1.5-9B-Chat-16K-Q3_K_M.gguf | 3 + Yi-1.5-9B-Chat-16K-Q3_K_S.gguf | 3 + Yi-1.5-9B-Chat-16K-Q4_0.gguf | 3 + Yi-1.5-9B-Chat-16K-Q4_K_M.gguf | 3 + Yi-1.5-9B-Chat-16K-Q4_K_S.gguf | 3 + Yi-1.5-9B-Chat-16K-Q5_0.gguf | 3 + Yi-1.5-9B-Chat-16K-Q5_K_M.gguf | 3 + Yi-1.5-9B-Chat-16K-Q5_K_S.gguf | 3 + Yi-1.5-9B-Chat-16K-Q6_K.gguf | 3 + Yi-1.5-9B-Chat-16K-Q8_0.gguf | 3 + Yi-1.5-9B-Chat-16K-f16.gguf | 3 + configuration.json | 1 + 16 files changed, 147 insertions(+), 57 deletions(-) create mode 100644 Yi-1.5-9B-Chat-16K-Q2_K.gguf create mode 100644 Yi-1.5-9B-Chat-16K-Q3_K_L.gguf create mode 100644 Yi-1.5-9B-Chat-16K-Q3_K_M.gguf create mode 100644 Yi-1.5-9B-Chat-16K-Q3_K_S.gguf create mode 100644 Yi-1.5-9B-Chat-16K-Q4_0.gguf create mode 100644 Yi-1.5-9B-Chat-16K-Q4_K_M.gguf create mode 100644 Yi-1.5-9B-Chat-16K-Q4_K_S.gguf create mode 100644 Yi-1.5-9B-Chat-16K-Q5_0.gguf create mode 100644 Yi-1.5-9B-Chat-16K-Q5_K_M.gguf create mode 100644 Yi-1.5-9B-Chat-16K-Q5_K_S.gguf create mode 100644 Yi-1.5-9B-Chat-16K-Q6_K.gguf create mode 100644 Yi-1.5-9B-Chat-16K-Q8_0.gguf create mode 100644 Yi-1.5-9B-Chat-16K-f16.gguf create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes index 886ac0c..64386eb 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 +Yi-1.5-9B-Chat-16K-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index db46c23..9567cff 100644 --- a/README.md +++ b/README.md @@ -1,47 +1,87 @@ --- -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 +base_model: 01-ai/Yi-1.5-9B-Chat-16K +inference: false +model_creator: 01-ai +model_name: Yi-1.5-9B-Chat-16 +model_type: yi +pipeline_tag: text-generation +quantized_by: Second State Inc. +license: apache-2.0 --- -### 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/Yi-1.5-9B-Chat-16K-GGUF') -``` -Git下载 -``` -#Git模型下载 -git clone https://www.modelscope.cn/second-state/Yi-1.5-9B-Chat-16K-GGUF.git -``` + + +
+ +
+
+ -

如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。

\ No newline at end of file +# Yi-1.5-9B-Chat-16K-GGUF + +## Original Model + +[01-ai/Yi-1.5-9B-Chat-16K](https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K) + +## Run with LlamaEdge + + + +- LlamaEdge version: coming soon +- +- 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: `16384` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-9B-Chat-16K-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template chatml \ + --reverse-prompt "<|im_end|>" \ + --ctx-size 16384 \ + --model-name Yi-1.5-9B-Chat-16K + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-9B-Chat-16K-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template chatml \ + --reverse-prompt "<|im_end|>" \ + --ctx-size 16384 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Yi-1.5-9B-Chat-16K-Q2_K.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q2_K.gguf) | Q2_K | 2 | 3.35 GB| smallest, significant quality loss - not recommended for most purposes | +| [Yi-1.5-9B-Chat-16K-Q3_K_L.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q3_K_L.gguf) | Q3_K_L | 3 | 4.69 GB| small, substantial quality loss | +| [Yi-1.5-9B-Chat-16K-Q3_K_M.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q3_K_M.gguf) | Q3_K_M | 3 | 4.32 GB| very small, high quality loss | +| [Yi-1.5-9B-Chat-16K-Q3_K_S.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q3_K_S.gguf) | Q3_K_S | 3 | 3.9 GB| very small, high quality loss | +| [Yi-1.5-9B-Chat-16K-Q4_0.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q4_0.gguf) | Q4_0 | 4 | 5.04 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Yi-1.5-9B-Chat-16K-Q4_K_M.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q4_K_M.gguf) | Q4_K_M | 4 | 5.33 GB| medium, balanced quality - recommended | +| [Yi-1.5-9B-Chat-16K-Q4_K_S.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q4_K_S.gguf) | Q4_K_S | 4 | 5.07 GB| small, greater quality loss | +| [Yi-1.5-9B-Chat-16K-Q5_0.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q5_0.gguf) | Q5_0 | 5 | 6.11 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Yi-1.5-9B-Chat-16K-Q5_K_M.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q5_K_M.gguf) | Q5_K_M | 5 | 6.26 GB| large, very low quality loss - recommended | +| [Yi-1.5-9B-Chat-16K-Q5_K_S.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q5_K_S.gguf) | Q5_K_S | 5 | 6.11 GB| large, low quality loss - recommended | +| [Yi-1.5-9B-Chat-16K-Q6_K.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q6_K.gguf) | Q6_K | 6 | 7.25 GB| very large, extremely low quality loss | +| [Yi-1.5-9B-Chat-16K-Q8_0.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q8_0.gguf) | Q8_0 | 8 | 9.38 GB| very large, extremely low quality loss - not recommended | +| [Yi-1.5-9B-Chat-16K-f16.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-f16.gguf) | f16 | 16 | 17.7 GB| | + +*Quantized with llama.cpp b3135* diff --git a/Yi-1.5-9B-Chat-16K-Q2_K.gguf b/Yi-1.5-9B-Chat-16K-Q2_K.gguf new file mode 100644 index 0000000..78ecbbe --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:393e36603d1f2dd5ee33a7da92d8037ebf0c927b5f2d51f2ffa0bc701ba996dd +size 3354325344 diff --git a/Yi-1.5-9B-Chat-16K-Q3_K_L.gguf b/Yi-1.5-9B-Chat-16K-Q3_K_L.gguf new file mode 100644 index 0000000..e7dad0d --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7ef02a3a22f5216faa9ed846d38ad06b39f431cee57f95be941665c1622c3e1 +size 4690751840 diff --git a/Yi-1.5-9B-Chat-16K-Q3_K_M.gguf b/Yi-1.5-9B-Chat-16K-Q3_K_M.gguf new file mode 100644 index 0000000..ce4ed3f --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50d81524d71d226366975842411da875f9ef0ceddba1187df03410392168b60e +size 4324405600 diff --git a/Yi-1.5-9B-Chat-16K-Q3_K_S.gguf b/Yi-1.5-9B-Chat-16K-Q3_K_S.gguf new file mode 100644 index 0000000..1c994f1 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36dbab3a75174fd8c6977b326b6580017eceb579a3f4b6c7b99a8aaef33e7ca8 +size 3899208032 diff --git a/Yi-1.5-9B-Chat-16K-Q4_0.gguf b/Yi-1.5-9B-Chat-16K-Q4_0.gguf new file mode 100644 index 0000000..b83fad5 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23c716476f24d772365d586866f2c11856c60e0c22d865365a2eb92b8f0efcfa +size 5036994912 diff --git a/Yi-1.5-9B-Chat-16K-Q4_K_M.gguf b/Yi-1.5-9B-Chat-16K-Q4_K_M.gguf new file mode 100644 index 0000000..315b15d --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3d9f179572523cc8c198b0ad2e05e94ea92eea4a5765d1cb1199e10e910f220 +size 5328957792 diff --git a/Yi-1.5-9B-Chat-16K-Q4_K_S.gguf b/Yi-1.5-9B-Chat-16K-Q4_K_S.gguf new file mode 100644 index 0000000..be83585 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac7f4a409f2a45d6e7b61441a314562d6beebdbe8199d7d2706cf1bf5473132 +size 5071860064 diff --git a/Yi-1.5-9B-Chat-16K-Q5_0.gguf b/Yi-1.5-9B-Chat-16K-Q5_0.gguf new file mode 100644 index 0000000..881b052 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17e8ad54081062e023997796b943a6a669430a6016c79a2c5f05b71f2f76dbb9 +size 6107853152 diff --git a/Yi-1.5-9B-Chat-16K-Q5_K_M.gguf b/Yi-1.5-9B-Chat-16K-Q5_K_M.gguf new file mode 100644 index 0000000..fbbd422 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca2ab962fb986ed5afad48417d7946a5301acac93c0d0e46f3385cf0977856f1 +size 6258258272 diff --git a/Yi-1.5-9B-Chat-16K-Q5_K_S.gguf b/Yi-1.5-9B-Chat-16K-Q5_K_S.gguf new file mode 100644 index 0000000..5f7b765 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:928d5aa97c8ab0240083afe2b0d756d3f2777ade0f944d1b3679ab84be4c0aeb +size 6107853152 diff --git a/Yi-1.5-9B-Chat-16K-Q6_K.gguf b/Yi-1.5-9B-Chat-16K-Q6_K.gguf new file mode 100644 index 0000000..61a6b58 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2d31e2f06c20bcbae60576fab54c007d895738679ec5ceee8c9d12a7827eee5 +size 7245640032 diff --git a/Yi-1.5-9B-Chat-16K-Q8_0.gguf b/Yi-1.5-9B-Chat-16K-Q8_0.gguf new file mode 100644 index 0000000..3bd72c3 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38892320ba6f7a98f1757637830666ec3f7dd2412f131ddac63a900509bc24c +size 9383915872 diff --git a/Yi-1.5-9B-Chat-16K-f16.gguf b/Yi-1.5-9B-Chat-16K-f16.gguf new file mode 100644 index 0000000..cc8be7a --- /dev/null +++ b/Yi-1.5-9B-Chat-16K-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:531283b57dd2c3c2e3a9a1667738ec493285ad7e3b5202d1f278a134a8cfc273 +size 17661112672 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