commit 1a7f086bc83b5ba5d9f80101e89f4546f8b382b7 Author: ModelHub XC Date: Mon Jun 15 10:16:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ec7277 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +gemma2-9b-cpt-sea-lionv3-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sea-lionv3-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sea-lionv3-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sea-lionv3-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sea-lionv3-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sea-lionv3-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sea-lionv3-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sea-lionv3-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e02c5eb --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: aisingapore/Gemma-SEA-LION-v3-9B-IT +language: +- en +- zh +- vi +- id +- th +- fil +- ta +- ms +- km +- lo +- my +- jv +- su +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/aisingapore/Gemma-SEA-LION-v3-9B-IT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma2-9b-cpt-sea-lionv3-instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sea-lionv3-instruct-GGUF/resolve/main/gemma2-9b-cpt-sea-lionv3-instruct.f16.gguf) | f16 | 18.6 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.IQ4_XS.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..2fed7ea --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8418390988629068e31dd8dbb5941f5980b9b6636e5f545dbe19481fc5af49a2 +size 5223171712 diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.Q2_K.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.Q2_K.gguf new file mode 100644 index 0000000..a4c0704 --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:513a28c095c89768a1b9b85111fbbee6387deab5ccb64029de59b2dc679e6adf +size 3805398656 diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_L.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..7370454 --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f161e2abeb4e992e8e5dc92836928a96e336753e6e08ba76946b27df6799b703 +size 5132453504 diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_M.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..7ab3e82 --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d8ef7a88e4fac01d0a5d856f30a5b316b306643d5c22b1de9500ac07f5e7b60 +size 4761781888 diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_S.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..472e1e5 --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e523f09f6d15bcc7e39f96ab8f734a9e46bc8093c14dfdd5ad9e0e354695ce4b +size 4337665664 diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.Q4_K_M.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..5031eba --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfef39c4844a36ecc99737c5e441dfc3b22176b3e97410a934fbd1e4e211dbb0 +size 5761058432 diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.Q4_K_S.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..9d3050f --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc88f3e1ccb46f48986f1fd920522a5d7626bf0a608eb08e5b0c65408a2ffe38 +size 5478925952 diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.Q5_K_M.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..93a10e2 --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce50657d86fe54cb36a48ccfde885a3bbe72a985a40450851343a8607a94b6a +size 6647367296 diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.Q5_K_S.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..0812dc6 --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c109a1043a90447e7e29713defadfb014c69699799c85144ef05aa74c98460cc +size 6483592832 diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.Q6_K.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.Q6_K.gguf new file mode 100644 index 0000000..3da3ba0 --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b327b509e05ec08078cb234138b54e2ef1fc4d9468e76b30f02f19e7c42f2f69 +size 7589070464 diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.Q8_0.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.Q8_0.gguf new file mode 100644 index 0000000..38b61b5 --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ac96dbe1c1711707256df6eb1c708c368aa83af48ff6357655cdb0a54f0f6b +size 9827149440 diff --git a/gemma2-9b-cpt-sea-lionv3-instruct.f16.gguf b/gemma2-9b-cpt-sea-lionv3-instruct.f16.gguf new file mode 100644 index 0000000..ad2173b --- /dev/null +++ b/gemma2-9b-cpt-sea-lionv3-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01eea99f070780367dc9b0613a4e1b77e2b20f92f1bcdc9627c63fffef29a53d +size 18490680960