commit 72a9593f028a7bf468870738b087176d1eee3822 Author: ModelHub XC Date: Thu Oct 8 12:06:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Gemma-2-9B-Chinese-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bdaf954 --- /dev/null +++ b/.gitattributes @@ -0,0 +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 +*.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 +Gemma-2-9B-Chinese-Chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Chinese-Chat-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma-2-9B-Chinese-Chat-Q2_K.gguf b/Gemma-2-9B-Chinese-Chat-Q2_K.gguf new file mode 100644 index 0000000..4f8e219 --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38fd29f2de941ff6820d7bc3014f7bb2956830abe1770e227464a5cefc688cae +size 3805398336 diff --git a/Gemma-2-9B-Chinese-Chat-Q3_K_L.gguf b/Gemma-2-9B-Chinese-Chat-Q3_K_L.gguf new file mode 100644 index 0000000..5e8a40d --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a86244179dd5817356996ac5ac0b5c50c5547e0691313f0aeff378bedaf569d +size 5132453184 diff --git a/Gemma-2-9B-Chinese-Chat-Q3_K_M.gguf b/Gemma-2-9B-Chinese-Chat-Q3_K_M.gguf new file mode 100644 index 0000000..35961ea --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b90c9deab6d9eb2b905813c26d51252c951342d1a115a5947c3f2c43c1281864 +size 4761781568 diff --git a/Gemma-2-9B-Chinese-Chat-Q3_K_S.gguf b/Gemma-2-9B-Chinese-Chat-Q3_K_S.gguf new file mode 100644 index 0000000..40f7896 --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c091b47bf0de9957e2dd9cda0803f847061cf966b25df3df1ef61c506c844f3 +size 4337665344 diff --git a/Gemma-2-9B-Chinese-Chat-Q4_0.gguf b/Gemma-2-9B-Chinese-Chat-Q4_0.gguf new file mode 100644 index 0000000..c4f6474 --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51fec844e9785a4990a2a4162bcce4220c1ff3dfeef889d0f2269a1dc727159b +size 5443142976 diff --git a/Gemma-2-9B-Chinese-Chat-Q4_K_M.gguf b/Gemma-2-9B-Chinese-Chat-Q4_K_M.gguf new file mode 100644 index 0000000..ac8ff72 --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:915797794ce8cded7d1eda142046605980fb62e8bcc04ed6ecb43bc419c29daf +size 5761058112 diff --git a/Gemma-2-9B-Chinese-Chat-Q4_K_S.gguf b/Gemma-2-9B-Chinese-Chat-Q4_K_S.gguf new file mode 100644 index 0000000..07ae989 --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c39082f397653a43d368922894dd408a12c3f994d58539d69552d5d021649554 +size 5478925632 diff --git a/Gemma-2-9B-Chinese-Chat-Q5_0.gguf b/Gemma-2-9B-Chinese-Chat-Q5_0.gguf new file mode 100644 index 0000000..8d15fcf --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c208bb333cc56cee436c9ae95ebcaea12dfb0b8bdc1591d49a76a852f19c526 +size 6483592512 diff --git a/Gemma-2-9B-Chinese-Chat-Q5_K_M.gguf b/Gemma-2-9B-Chinese-Chat-Q5_K_M.gguf new file mode 100644 index 0000000..8e16cdd --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd30f308b13b770e507e0b42f4e274476267ffa2e1feb2d8ce6dc5d9034dd1ee +size 6647366976 diff --git a/Gemma-2-9B-Chinese-Chat-Q5_K_S.gguf b/Gemma-2-9B-Chinese-Chat-Q5_K_S.gguf new file mode 100644 index 0000000..1d0a705 --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1cdc271a6c716a167f3c339b74ec8218b1e2a787ef65a1a9e8d80ebd1921df2 +size 6483592512 diff --git a/Gemma-2-9B-Chinese-Chat-Q6_K.gguf b/Gemma-2-9B-Chinese-Chat-Q6_K.gguf new file mode 100644 index 0000000..f24f1d5 --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d17fc02831b3a1f34b60e3399721f5deb042b038c0f4c769f031d99db8de8614 +size 7589070144 diff --git a/Gemma-2-9B-Chinese-Chat-Q8_0.gguf b/Gemma-2-9B-Chinese-Chat-Q8_0.gguf new file mode 100644 index 0000000..b9c8f8b --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492e309a5df1b6d2193c18a9891178c825087139fcb8260c4b2329de1f1251a8 +size 9827149120 diff --git a/Gemma-2-9B-Chinese-Chat-f16.gguf b/Gemma-2-9B-Chinese-Chat-f16.gguf new file mode 100644 index 0000000..6757686 --- /dev/null +++ b/Gemma-2-9B-Chinese-Chat-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e68a3c25e0658d330e9cacc397bde8eaf16deee9f3494ceffb39ab37e479033 +size 18490680640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..01ceb75 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +license: gemma +library_name: transformers +pipeline_tag: text-generation +base_model: shenzhi-wang/Gemma-2-9B-Chinese-Chat +inference: false +model_creator: shenzhi-wang +model_name: Gemma-2-9B-Chinese-Chat +quantized_by: Second State Inc. +language: +- en +- zh +--- + + + +
+ +
+
+ + +# Gemma-2-9B-Chinese-Chat-GGUF + +## Original Model + +[shenzhi-wang/Gemma-2-9B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Gemma-2-9B-Chinese-Chat) + +## 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-2-9B-Chinese-Chat-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template gemma-instruct \ + --ctx-size 8192 \ + --model-name gemma-2-9b + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. \ + --nn-preload default:GGML:AUTO:Gemma-2-9B-Chinese-Chat-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-2-9B-Chinese-Chat-Q2_K.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q2_K.gguf) | Q2_K | 2 | 3.81 GB| smallest, significant quality loss - not recommended for most purposes | +| [Gemma-2-9B-Chinese-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 5.13 GB| small, substantial quality loss | +| [Gemma-2-9B-Chinese-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 4.76 GB| very small, high quality loss | +| [Gemma-2-9B-Chinese-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 4.34 GB| very small, high quality loss | +| [Gemma-2-9B-Chinese-Chat-Q4_0.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q4_0.gguf) | Q4_0 | 4 | 5.44 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Gemma-2-9B-Chinese-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 5.76 GB| medium, balanced quality - recommended | +| [Gemma-2-9B-Chinese-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 5.48 GB| small, greater quality loss | +| [Gemma-2-9B-Chinese-Chat-Q5_0.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q5_0.gguf) | Q5_0 | 5 | 6.48 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Gemma-2-9B-Chinese-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 6.65 GB| large, very low quality loss - recommended | +| [Gemma-2-9B-Chinese-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 6.48 GB| large, low quality loss - recommended | +| [Gemma-2-9B-Chinese-Chat-Q6_K.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q6_K.gguf) | Q6_K | 6 | 7.59 GB| very large, extremely low quality loss | +| [Gemma-2-9B-Chinese-Chat-Q8_0.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-Q8_0.gguf) | Q8_0 | 8 | 9.83 GB| very large, extremely low quality loss - not recommended | +| [Gemma-2-9B-Chinese-Chat-f16.gguf](https://huggingface.co/second-state/Gemma-2-9B-Chinese-Chat-GGUF/blob/main/Gemma-2-9B-Chinese-Chat-f16.gguf) | f16 | 16 | 18.5 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..8caf7fe --- /dev/null +++ b/config.json @@ -0,0 +1,34 @@ +{ + "_name_or_path": "shenzhi-wang/Gemma-2-9B-Chinese-Chat", + "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": 256, + "hidden_act": "gelu_pytorch_tanh", + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "model_type": "gemma2", + "num_attention_heads": 16, + "num_hidden_layers": 42, + "num_key_value_heads": 8, + "pad_token_id": 0, + "query_pre_attn_scalar": 224, + "rms_norm_eps": 1e-06, + "rope_theta": 10000.0, + "sliding_window": 4096, + "sliding_window_size": 4096, + "torch_dtype": "bfloat16", + "transformers_version": "4.42.2", + "use_cache": false, + "vocab_size": 256000 +} 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