commit 86b45c11cf82ba1c8afe960f5a8ed2178291a00d Author: ModelHub XC Date: Mon Jul 13 05:52:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: SanctumAI/gemma-2-9b-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2a86e7f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.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-it.f16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6d2cf96 --- /dev/null +++ b/README.md @@ -0,0 +1,58 @@ +--- +license: gemma +pipeline_tag: text-generation +tags: +- conversational +base_model: +- google/gemma-2-9b-it +--- + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/64a28db2f1968b7d7f357182/u7s05Lc_DIwrI3mY_Hzwn.png) +*This model was quantized by [SanctumAI](https://sanctum.ai). To leave feedback, join our community in [Discord](https://discord.gg/7ZNE78HJKh).* + +# Gemma 2 9B IT GGUF + +**Model creator:** [google](https://huggingface.co/google)
+**Original model**: [gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it)
+ +## Model Summary: + +Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights for both pre-trained variants and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. + +## Prompt Template: + +If you're using Sanctum app, simply use `Gemma` model preset. + +Prompt template: + +``` +user +{prompt} +<|start_of_turn|>model +``` + +## Hardware Requirements Estimate + +| Name | Quant method | Size | Memory (RAM, vRAM) required | +| ---- | ---- | ---- | ---- | +| [gemma-2-9b-it.Q2_K.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q2_K.gguf) | Q2_K | 3.81 GB | 15.14 GB | +| [gemma-2-9b-it.Q3_K_S.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q3_K_S.gguf) | Q3_K_S | 4.34 GB | 15.64 GB | +| [gemma-2-9b-it.Q3_K_M.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q3_K_M.gguf) | Q3_K_M | 4.76 GB | 16.04 GB | +| [gemma-2-9b-it.Q3_K_L.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q3_K_L.gguf) | Q3_K_L | 5.13 GB | 16.38 GB | +| [gemma-2-9b-it.Q4_0.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q4_0.gguf) | Q4_0 | 5.44 GB | 16.67 GB | +| [gemma-2-9b-it.Q4_K_S.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q4_K_S.gguf) | Q4_K_S | 5.48 GB | 16.70 GB | +| [gemma-2-9b-it.Q4_K_M.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q4_K_M.gguf) | Q4_K_M | 5.76 GB | 16.97 GB | +| [gemma-2-9b-it.Q4_K.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q4_K.gguf) | Q4_K | 5.76 GB | 16.97 GB | +| [gemma-2-9b-it.Q4_1.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q4_1.gguf) | Q4_1 | 5.96 GB | 17.15 GB | +| [gemma-2-9b-it.Q5_0.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q5_0.gguf) | Q5_0 | 6.48 GB | 17.64 GB | +| [gemma-2-9b-it.Q5_K_S.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q5_K_S.gguf) | Q5_K_S | 6.48 GB | 17.64 GB | +| [gemma-2-9b-it.Q5_K_M.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q5_K_M.gguf) | Q5_K_M | 6.65 GB | 17.79 GB | +| [gemma-2-9b-it.Q5_K.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q5_K.gguf) | Q5_K | 6.65 GB | 17.79 GB | +| [gemma-2-9b-it.Q5_1.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q5_1.gguf) | Q5_1 | 7.00 GB | 18.12 GB | +| [gemma-2-9b-it.Q6_K.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q6_K.gguf) | Q6_K | 7.59 GB | 18.67 GB | +| [gemma-2-9b-it.Q8_0.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.Q8_0.gguf) | Q8_0 | 9.83 GB | 20.75 GB | +| [gemma-2-9b-it.f16.gguf](https://huggingface.co/SanctumAI/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it.f16.gguf) | f16 | 18.49 GB | 28.82 GB | + +## Disclaimer + +Sanctum is not the creator, originator, or owner of any Model featured in the Models section of the Sanctum application. Each Model is created and provided by third parties. Sanctum does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Model listed there. You understand that supported Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Model is the sole responsibility of the person or entity who originated such Model. Sanctum may not monitor or control the Models supported and cannot, and does not, take responsibility for any such Model. Sanctum disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Models. Sanctum further disclaims any warranty that the Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Models, your downloading of any Model, or use of any other Model provided by or through Sanctum. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a459509 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "gemma2" +} \ No newline at end of file diff --git a/gemma-2-9b-it.Q2_K.gguf b/gemma-2-9b-it.Q2_K.gguf new file mode 100644 index 0000000..71a541d --- /dev/null +++ b/gemma-2-9b-it.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6dc51397e0d2ff87cdd3b759007c4f9dbbc9067bfa112a4aa2be6bfcc078f40 +size 3805397696 diff --git a/gemma-2-9b-it.Q3_K_L.gguf b/gemma-2-9b-it.Q3_K_L.gguf new file mode 100644 index 0000000..dc86ede --- /dev/null +++ b/gemma-2-9b-it.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b8ad7f02b29304530dd7067e694f86ad554c72530029910cfe114229bf5dee2 +size 5132452544 diff --git a/gemma-2-9b-it.Q3_K_M.gguf b/gemma-2-9b-it.Q3_K_M.gguf new file mode 100644 index 0000000..218d274 --- /dev/null +++ b/gemma-2-9b-it.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:134d1caf7a05311acde0f7984ddeb6c1386a2ad0d3977dae3750e49fbbe0c964 +size 4761780928 diff --git a/gemma-2-9b-it.Q3_K_S.gguf b/gemma-2-9b-it.Q3_K_S.gguf new file mode 100644 index 0000000..7ecf0ff --- /dev/null +++ b/gemma-2-9b-it.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389a070a115c2ce1b19a61840372f3fb2a1610b7b8fd714426c6331657f66fd0 +size 4337664704 diff --git a/gemma-2-9b-it.Q4_0.gguf b/gemma-2-9b-it.Q4_0.gguf new file mode 100644 index 0000000..6f3417d --- /dev/null +++ b/gemma-2-9b-it.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cd8c8a2ecb850d39c80f52e7d45f495e8479115a886741bd06fbfcaf9f73d39 +size 5443142336 diff --git a/gemma-2-9b-it.Q4_1.gguf b/gemma-2-9b-it.Q4_1.gguf new file mode 100644 index 0000000..bdf67a0 --- /dev/null +++ b/gemma-2-9b-it.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab6b6042f0500b4bf07e95a4010b58b9c74335c75df74d330f85d165e5e0a627 +size 5963367104 diff --git a/gemma-2-9b-it.Q4_K.gguf b/gemma-2-9b-it.Q4_K.gguf new file mode 100644 index 0000000..bd3f054 --- /dev/null +++ b/gemma-2-9b-it.Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd64cf29d76294581acfad6dad9eff932bad1b8de7256e4d9d66569b0ef6748b +size 5761057472 diff --git a/gemma-2-9b-it.Q4_K_M.gguf b/gemma-2-9b-it.Q4_K_M.gguf new file mode 100644 index 0000000..bd3f054 --- /dev/null +++ b/gemma-2-9b-it.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd64cf29d76294581acfad6dad9eff932bad1b8de7256e4d9d66569b0ef6748b +size 5761057472 diff --git a/gemma-2-9b-it.Q4_K_S.gguf b/gemma-2-9b-it.Q4_K_S.gguf new file mode 100644 index 0000000..b27259e --- /dev/null +++ b/gemma-2-9b-it.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff3d6749f0bfc4b954ddedbe49923aefecc4198d7b2cb45dbdf0be809cd2c34d +size 5478924992 diff --git a/gemma-2-9b-it.Q5_0.gguf b/gemma-2-9b-it.Q5_0.gguf new file mode 100644 index 0000000..bfd3767 --- /dev/null +++ b/gemma-2-9b-it.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f1c09d68353afb9fdd8a2d53df9c2b43642f6ebc1ba6fab22eec4d3c6c142d7 +size 6483591872 diff --git a/gemma-2-9b-it.Q5_1.gguf b/gemma-2-9b-it.Q5_1.gguf new file mode 100644 index 0000000..472aa81 --- /dev/null +++ b/gemma-2-9b-it.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d8cbcdd25e5a60aaf1bffd0837bf999f74ce26cca518621cc570485d16cedee +size 7003816640 diff --git a/gemma-2-9b-it.Q5_K.gguf b/gemma-2-9b-it.Q5_K.gguf new file mode 100644 index 0000000..871fb6d --- /dev/null +++ b/gemma-2-9b-it.Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:252b05b32ee6169f46b0e938f64b7b65f269bedc371ffb897ad5cbb2262e1de7 +size 6647366336 diff --git a/gemma-2-9b-it.Q5_K_M.gguf b/gemma-2-9b-it.Q5_K_M.gguf new file mode 100644 index 0000000..871fb6d --- /dev/null +++ b/gemma-2-9b-it.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:252b05b32ee6169f46b0e938f64b7b65f269bedc371ffb897ad5cbb2262e1de7 +size 6647366336 diff --git a/gemma-2-9b-it.Q5_K_S.gguf b/gemma-2-9b-it.Q5_K_S.gguf new file mode 100644 index 0000000..7c40919 --- /dev/null +++ b/gemma-2-9b-it.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c4aa1577e805a35adfd2cd1701252a338cd1e829e746ab9903936bbfa8ea6c +size 6483591872 diff --git a/gemma-2-9b-it.Q6_K.gguf b/gemma-2-9b-it.Q6_K.gguf new file mode 100644 index 0000000..21d79ed --- /dev/null +++ b/gemma-2-9b-it.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae6dfd13a48ef717b6bd6d8030ca9ee8066ebbd2ef0ca690d39234d3caeebc7 +size 7589069504 diff --git a/gemma-2-9b-it.Q8_0.gguf b/gemma-2-9b-it.Q8_0.gguf new file mode 100644 index 0000000..de6b075 --- /dev/null +++ b/gemma-2-9b-it.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:399ac085a1814916bf309e7b622e5a91aadaee839a77c26dcc534d17c7af429a +size 9827148480 diff --git a/gemma-2-9b-it.f16.gguf b/gemma-2-9b-it.f16.gguf new file mode 100644 index 0000000..44bf6ea --- /dev/null +++ b/gemma-2-9b-it.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b91fd4a448d3c7080795a0adb11c832e68abc6e295fa2eb5b21d97b54399fffe +size 18490680000