初始化项目，由ModelHub XC社区提供模型

Model: second-state/gemma-3-12b-it-GGUF Source: Original Platform
2026-10-11 10:43:17 +08:00
commit f8d0748a15
17 changed files with 230 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +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
+*.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-3-12b-it-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-f16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,99 @@
+---
+base_model: google/gemma-3-12b-it
+inference: false
+library_name: transformers
+license: gemma
+model_creator: Google
+model_name: gemma-3-12b-it
+quantized_by: Second State Inc.
+pipeline_tag: image-text-to-text
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# Gemma-3-12b-it-GGUF
+
+## Original Model
+
+[google/gemma-3-12b-it](https://huggingface.co/google/gemma-3-12b-it)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.18.5](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.18.5) and above
+
+- Prompt template
+
+  - Prompt type: `gemma-3`
+
+  - Prompt string
+
+    ```text
+    <bos><start_of_turn>user
+    {user_message}<end_of_turn>
+    <start_of_turn>model
+    {model_message}<end_of_turn>model
+    ```
+
+- Context size: `128000`
+
+- Run as LlamaEdge service
+
+  - Chat
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-3-12b-it-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template gemma-3 \
+      --ctx-size 128000 \
+      --model-name gemma-3-12b
+    ```
+
+  - Images
+ 
+    **Note that input images are required to be normalized to 896 x 896 resolution and encoded to 256 tokens each**
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-3-12b-it-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template gemma-3 \
+      --llava-mmproj gemma-3-12b-it-mmproj-f16.gguf \
+      --ctx-size 128000 \
+      --model-name gemma-3-12b
+    ``` 
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. \
+    --nn-preload default:GGML:AUTO:gemma-3-12b-it-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template gemma-3 \
+    --ctx-size 128000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [gemma-3-12b-it-Q2_K.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q2_K.gguf)     | Q2_K   | 2 | 4.77 GB| smallest, significant quality loss - not recommended for most purposes |
+| [gemma-3-12b-it-Q3_K_L.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q3_K_L.gguf) | Q3_K_L | 3 | 6.48 GB| small, substantial quality loss |
+| [gemma-3-12b-it-Q3_K_M.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q3_K_M.gguf) | Q3_K_M | 3 | 6.01 GB| very small, high quality loss |
+| [gemma-3-12b-it-Q3_K_S.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q3_K_S.gguf) | Q3_K_S | 3 | 5.46 GB| very small, high quality loss |
+| [gemma-3-12b-it-Q4_0.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q4_0.gguf)     | Q4_0   | 4 | 6.89 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [gemma-3-12b-it-Q4_K_M.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q4_K_M.gguf) | Q4_K_M | 4 | 7.30 GB| medium, balanced quality - recommended |
+| [gemma-3-12b-it-Q4_K_S.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q4_K_S.gguf) | Q4_K_S | 4 | 6.94 GB| small, greater quality loss |
+| [gemma-3-12b-it-Q5_0.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q5_0.gguf)     | Q5_0   | 5 | 8.23 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [gemma-3-12b-it-Q5_K_M.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q5_K_M.gguf) | Q5_K_M | 5 | 8.44 GB| large, very low quality loss - recommended |
+| [gemma-3-12b-it-Q5_K_S.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q5_K_S.gguf) | Q5_K_S | 5 | 8.23 GB| large, low quality loss - recommended |
+| [gemma-3-12b-it-Q6_K.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q6_K.gguf)     | Q6_K   | 6 | 9.66 GB| very large, extremely low quality loss |
+| [gemma-3-12b-it-Q8_0.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-Q8_0.gguf)     | Q8_0   | 8 | 12.5 GB| very large, extremely low quality loss - not recommended |
+| [gemma-3-12b-it-f16.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-f16.gguf)       | f16    | 16 | 23.5 GB|  |
+| [gemma-3-12b-it-mmproj-f16.gguf](https://huggingface.co/second-state/gemma-3-12b-it-GGUF/blob/main/gemma-3-12b-it-mmproj-f16.gguf)       | f16   | 16 | 854 MB|  |
+
+*Quantized with llama.cpp b4875*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "hidden_size": 3840,
+    "intermediate_size": 15360,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "sliding_window": 1024
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}
--- a/gemma-3-12b-it-Q2_K.gguf
+++ b/gemma-3-12b-it-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d69dbd3b54bd0d07dbb7c29ff3dd8cffb3c50f99e142d7ee7efd47d33b5a98
+size 4768018176
--- a/gemma-3-12b-it-Q3_K_L.gguf
+++ b/gemma-3-12b-it-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daed16cb233caac32f463531b1557d06e7bea318ea19914431beb987e588bbf3
+size 6479982336
--- a/gemma-3-12b-it-Q3_K_M.gguf
+++ b/gemma-3-12b-it-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63c8979532290a52f547da36ccf753f9958f18b4b01fa35d65213a8f4677b9f
+size 6008614656
--- a/gemma-3-12b-it-Q3_K_S.gguf
+++ b/gemma-3-12b-it-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f370595016d11ccd84a72e759fc9e97614db9b5962f7f9b6a513199791d42cc7
+size 5458112256
--- a/gemma-3-12b-it-Q4_0.gguf
+++ b/gemma-3-12b-it-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f2b1d67f3ce1e6ff5e1a24bf7c4c431b75fcc5c4a717ba7c95f79ac47f69d3
+size 6886960896
--- a/gemma-3-12b-it-Q4_K_M.gguf
+++ b/gemma-3-12b-it-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb69bff3f48a7b642355d64a90e481182a7794707b3133890646b1efa778ff5
+size 7300574976
--- a/gemma-3-12b-it-Q4_K_S.gguf
+++ b/gemma-3-12b-it-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0508a2ec2714d8f21405f3c6c8b187287aeaf70af03ce5a5c2d56c515dd341e5
+size 6935129856
--- a/gemma-3-12b-it-Q5_0.gguf
+++ b/gemma-3-12b-it-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e98eb8789477417e320fa0a849654daa4c316f2a27e2362a0cc336661599d5
+size 8231759616
--- a/gemma-3-12b-it-Q5_K_M.gguf
+++ b/gemma-3-12b-it-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2143c5bed44228438385ecc43ddcbe6ea7e02950e23adaa5661690f40a49db
+size 8444833536
--- a/gemma-3-12b-it-Q5_K_S.gguf
+++ b/gemma-3-12b-it-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d13e4655f4c1cc6ab73603b3e257a6afc65cb9fea3254c80dc9ed07ad10261
+size 8231759616
--- a/gemma-3-12b-it-Q6_K.gguf
+++ b/gemma-3-12b-it-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8253acac0a41312ffc8560ebfe64b66122c3dc5754059f7bb2900223dae3b6
+size 9660608256
--- a/gemma-3-12b-it-Q8_0.gguf
+++ b/gemma-3-12b-it-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:915076d5c03619f4cc2ca88c6ee6fdbda60f0337fe7ca9c037d817517826bc43
+size 12509949696
--- a/gemma-3-12b-it-f16.gguf
+++ b/gemma-3-12b-it-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78cd8535609c7b1c517c2b6a2f2935486e915e116f9d74863a8e787e1c08ef44
+size 23539658496
--- a/gemma-3-12b-it-mmproj-f16.gguf
+++ b/gemma-3-12b-it-mmproj-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c02d056410848227001830866e0a269fcc28aaf8ca971bded494003de9f5a5
+size 854200224