From 20af7fc56a6e7017f3dc118311ac9d9b621710a2 Mon Sep 17 00:00:00 2001 From: ai-modelscope Date: Tue, 29 Oct 2024 13:52:29 +0800 Subject: [PATCH] Update README.md --- .gitattributes | 40 +++++--- README.md | 129 ++++++++++++++++--------- config.json | 33 +++++++ gemma-2-27b-it-Q2_K.gguf | 3 + gemma-2-27b-it-Q3_K_L.gguf | 3 + gemma-2-27b-it-Q3_K_M.gguf | 3 + gemma-2-27b-it-Q3_K_S.gguf | 3 + gemma-2-27b-it-Q4_K_M.gguf | 3 + gemma-2-27b-it-Q4_K_S.gguf | 3 + gemma-2-27b-it-Q5_0.gguf | 3 + gemma-2-27b-it-Q5_K_M.gguf | 3 + gemma-2-27b-it-Q5_K_S.gguf | 3 + gemma-2-27b-it-Q6_K.gguf | 3 + gemma-2-27b-it-f16-00001-of-00002.gguf | 3 + gemma-2-27b-it-f16-00002-of-00002.gguf | 3 + 15 files changed, 176 insertions(+), 62 deletions(-) create mode 100644 config.json create mode 100644 gemma-2-27b-it-Q2_K.gguf create mode 100644 gemma-2-27b-it-Q3_K_L.gguf create mode 100644 gemma-2-27b-it-Q3_K_M.gguf create mode 100644 gemma-2-27b-it-Q3_K_S.gguf create mode 100644 gemma-2-27b-it-Q4_K_M.gguf create mode 100644 gemma-2-27b-it-Q4_K_S.gguf create mode 100644 gemma-2-27b-it-Q5_0.gguf create mode 100644 gemma-2-27b-it-Q5_K_M.gguf create mode 100644 gemma-2-27b-it-Q5_K_S.gguf create mode 100644 gemma-2-27b-it-Q6_K.gguf create mode 100644 gemma-2-27b-it-f16-00001-of-00002.gguf create mode 100644 gemma-2-27b-it-f16-00002-of-00002.gguf diff --git a/.gitattributes b/.gitattributes index 11a9c76..32b3d7f 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,39 +1,49 @@ *.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 +gemma-2-27b-it-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-f16-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-27b-it-f16-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index b302e9d..b7be28b 100644 --- a/README.md +++ b/README.md @@ -1,51 +1,86 @@ --- -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 +base_model: google/gemma-2-27b-it +inference: false +license: gemma +library_name: transformers +pipeline_tag: text-generation +model_creator: Google +model_name: gemma-2-27b-it +quantized_by: Second State Inc. +tags: +- conversational --- -### 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/gemma-2-27b-it-GGUF') -``` -Git下载 -``` -#Git模型下载 -git clone https://www.modelscope.cn/second-state/gemma-2-27b-it-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 +# Gemma-2-27b-it-GGUF + +## Original Model + +[google/gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.12.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.1) and above + +- Prompt template + + - Prompt type: `gemma-instruct` + + - Prompt string + + ```text + user + {user_message} + model + {model_message}model + ``` + +- Context size: `8192` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-2-27b-it-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template gemma-instruct \ + --ctx-size 8192 \ + --model-name gemma-2-27b + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. \ + --nn-preload default:GGML:AUTO:gemma-2-27b-it-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template gemma-instruct \ + --ctx-size 8192 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [gemma-2-27b-it-Q2_K.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q2_K.gguf) | Q2_K | 2 | 10.4 GB| smallest, significant quality loss - not recommended for most purposes | +| [gemma-2-27b-it-Q3_K_L.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q3_K_L.gguf) | Q3_K_L | 3 | 14.5 GB| small, substantial quality loss | +| [gemma-2-27b-it-Q3_K_M.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q3_K_M.gguf) | Q3_K_M | 3 | 13.4 GB| very small, high quality loss | +| [gemma-2-27b-it-Q3_K_S.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q3_K_S.gguf) | Q3_K_S | 3 | 12.2 GB| very small, high quality loss | +| [gemma-2-27b-it-Q4_0.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q4_0.gguf) | Q4_0 | 4 | 15.6 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [gemma-2-27b-it-Q4_K_M.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q4_K_M.gguf) | Q4_K_M | 4 | 16.6 GB| medium, balanced quality - recommended | +| [gemma-2-27b-it-Q4_K_S.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q4_K_S.gguf) | Q4_K_S | 4 | 15.7 GB| small, greater quality loss | +| [gemma-2-27b-it-Q5_0.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q5_0.gguf) | Q5_0 | 5 | 18.9 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [gemma-2-27b-it-Q5_K_M.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q5_K_M.gguf) | Q5_K_M | 5 | 19.4 GB| large, very low quality loss - recommended | +| [gemma-2-27b-it-Q5_K_S.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q5_K_S.gguf) | Q5_K_S | 5 | 18.9 GB| large, low quality loss - recommended | +| [gemma-2-27b-it-Q6_K.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q6_K.gguf) | Q6_K | 6 | 22.3 GB| very large, extremely low quality loss | +| [gemma-2-27b-it-Q8_0.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-Q8_0.gguf) | Q8_0 | 8 | 28.9 GB| very large, extremely low quality loss - not recommended | +| [gemma-2-27b-it-f16-00001-of-00002.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-f16-00001-of-00002.gguf) | f16 | 16 | 29.9 GB| | +| [gemma-2-27b-it-f16-00002-of-00002.gguf](https://huggingface.co/second-state/gemma-2-27b-it-GGUF/blob/main/gemma-2-27b-it-f16-00002-of-00002.gguf) | f16 | 16 | 24.6 GB| | + +*Quantized with llama.cpp b3259* \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..2f1eb57 --- /dev/null +++ b/config.json @@ -0,0 +1,33 @@ +{ + "architectures": [ + "Gemma2ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": 50.0, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 1, + "final_logit_softcapping": 30.0, + "head_dim": 128, + "hidden_act": "gelu_pytorch_tanh", + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 4608, + "initializer_range": 0.02, + "intermediate_size": 36864, + "max_position_embeddings": 8192, + "model_type": "gemma2", + "num_attention_heads": 32, + "num_hidden_layers": 46, + "num_key_value_heads": 16, + "pad_token_id": 0, + "query_pre_attn_scalar": 144, + "rms_norm_eps": 1e-06, + "rope_theta": 10000.0, + "sliding_window": 4096, + "sliding_window_size": 4096, + "torch_dtype": "bfloat16", + "transformers_version": "4.42.0.dev0", + "use_cache": true, + "vocab_size": 256000 +} diff --git a/gemma-2-27b-it-Q2_K.gguf b/gemma-2-27b-it-Q2_K.gguf new file mode 100644 index 0000000..395258f --- /dev/null +++ b/gemma-2-27b-it-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74573055f1f2083cd18c29c83766b6cc216b75a35e8236c6fec27ebe7ad2514b +size 10449576032 diff --git a/gemma-2-27b-it-Q3_K_L.gguf b/gemma-2-27b-it-Q3_K_L.gguf new file mode 100644 index 0000000..df2b4d7 --- /dev/null +++ b/gemma-2-27b-it-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d476534b00c3f09ff5c11ccffad7789b216176fbc99d486a3a151d16473b3f8a +size 14519361632 diff --git a/gemma-2-27b-it-Q3_K_M.gguf b/gemma-2-27b-it-Q3_K_M.gguf new file mode 100644 index 0000000..45937ef --- /dev/null +++ b/gemma-2-27b-it-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e7ce3e26137e2d9559cee01229226852655be01229d967f4d8496bca5cef0f +size 13424648288 diff --git a/gemma-2-27b-it-Q3_K_S.gguf b/gemma-2-27b-it-Q3_K_S.gguf new file mode 100644 index 0000000..e7cfd8f --- /dev/null +++ b/gemma-2-27b-it-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2c86da06c74bbeed911ad3cd4d876ed21ee9618ef3af41f0e8aee42dfab1343 +size 12169060448 diff --git a/gemma-2-27b-it-Q4_K_M.gguf b/gemma-2-27b-it-Q4_K_M.gguf new file mode 100644 index 0000000..2417471 --- /dev/null +++ b/gemma-2-27b-it-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb052c865ed92957c7a6820d028ce39297f33d9a86c77fed7c7cd463785cb95b +size 16645382240 diff --git a/gemma-2-27b-it-Q4_K_S.gguf b/gemma-2-27b-it-Q4_K_S.gguf new file mode 100644 index 0000000..dfd8e28 --- /dev/null +++ b/gemma-2-27b-it-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef65ae05888d5ea3fc0b44ca5f34c14b7fce87e561268f3aae231a9210a6fe4f +size 15739265120 diff --git a/gemma-2-27b-it-Q5_0.gguf b/gemma-2-27b-it-Q5_0.gguf new file mode 100644 index 0000000..3096092 --- /dev/null +++ b/gemma-2-27b-it-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cac4390d785c7113b1e89fd0d20b0799d97771068ec22e0f8051baa574d2c6d +size 18884206688 diff --git a/gemma-2-27b-it-Q5_K_M.gguf b/gemma-2-27b-it-Q5_K_M.gguf new file mode 100644 index 0000000..25b90cc --- /dev/null +++ b/gemma-2-27b-it-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9240c09c544a518ea51b4358dd7b91ac6deda22deeacf2ebcf0b4b95fa5ec04 +size 19408117856 diff --git a/gemma-2-27b-it-Q5_K_S.gguf b/gemma-2-27b-it-Q5_K_S.gguf new file mode 100644 index 0000000..6c74449 --- /dev/null +++ b/gemma-2-27b-it-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:925151ff3173773fe1ea8152c58d38f1a4ea10b10afbff9e02d01ac9bd4d3863 +size 18884206688 diff --git a/gemma-2-27b-it-Q6_K.gguf b/gemma-2-27b-it-Q6_K.gguf new file mode 100644 index 0000000..9824c08 --- /dev/null +++ b/gemma-2-27b-it-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91efe1ff49f437fa493da1a7712cf9a9a7dacc8157f12b380d87806fb4dbdb90 +size 22343524448 diff --git a/gemma-2-27b-it-f16-00001-of-00002.gguf b/gemma-2-27b-it-f16-00001-of-00002.gguf new file mode 100644 index 0000000..6237c7d --- /dev/null +++ b/gemma-2-27b-it-f16-00001-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ab4bffc57f5fb61e4cd11cd087aa4fe55aac097a976c7043edb5ad824a48202 +size 29885958144 diff --git a/gemma-2-27b-it-f16-00002-of-00002.gguf b/gemma-2-27b-it-f16-00002-of-00002.gguf new file mode 100644 index 0000000..c5f2298 --- /dev/null +++ b/gemma-2-27b-it-f16-00002-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3990b5bdf739ed56f245a3e4de261b4a50e551355173fc7c80de93d43041386 +size 24576063776