commit eada71babb0a3f4e4f82284f802bd0bd5f37c26f Author: ModelHub XC Date: Sat May 16 04:13:29 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GrayLine-Gemma3-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f155798 --- /dev/null +++ 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 +GrayLine-Gemma3-4B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GrayLine-Gemma3-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GrayLine-Gemma3-4B.IQ4_XS.gguf b/GrayLine-Gemma3-4B.IQ4_XS.gguf new file mode 100644 index 0000000..4116fb5 --- /dev/null +++ b/GrayLine-Gemma3-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf09fc73e0222e9bfc7e0e963fcc2fab1c50a45b6d32ff368f87119ed8b2eb5 +size 2279626688 diff --git a/GrayLine-Gemma3-4B.Q2_K.gguf b/GrayLine-Gemma3-4B.Q2_K.gguf new file mode 100644 index 0000000..f47d504 --- /dev/null +++ b/GrayLine-Gemma3-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:544ff9245b91d86c2a6058623cb4b0ba2789ffc0c42f18bc74c917aa9a821344 +size 1729165248 diff --git a/GrayLine-Gemma3-4B.Q3_K_L.gguf b/GrayLine-Gemma3-4B.Q3_K_L.gguf new file mode 100644 index 0000000..681b225 --- /dev/null +++ b/GrayLine-Gemma3-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0a59ac9c0ed841743e8bc0048a82fec35c3f49119801d18c18458b4ff16fa86 +size 2236086208 diff --git a/GrayLine-Gemma3-4B.Q3_K_M.gguf b/GrayLine-Gemma3-4B.Q3_K_M.gguf new file mode 100644 index 0000000..ade0468 --- /dev/null +++ b/GrayLine-Gemma3-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6660e0a4e9a423b892a6e415443ad6e9240d4e4a69a369919911f91ee54bc12 +size 2098460608 diff --git a/GrayLine-Gemma3-4B.Q3_K_S.gguf b/GrayLine-Gemma3-4B.Q3_K_S.gguf new file mode 100644 index 0000000..e18a71b --- /dev/null +++ b/GrayLine-Gemma3-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c627b185703f7114e9ef02ddb72fd9b825e6a88a85e098eca3e852cdb9f11b +size 1937364928 diff --git a/GrayLine-Gemma3-4B.Q4_K_M.gguf b/GrayLine-Gemma3-4B.Q4_K_M.gguf new file mode 100644 index 0000000..6aec3a9 --- /dev/null +++ b/GrayLine-Gemma3-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b550b7fd415db3f68583f55be9075530ec142220b3f53eb8742333c12d8ea7 +size 2489894848 diff --git a/GrayLine-Gemma3-4B.Q4_K_S.gguf b/GrayLine-Gemma3-4B.Q4_K_S.gguf new file mode 100644 index 0000000..416933f --- /dev/null +++ b/GrayLine-Gemma3-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa3cb3cfed0b341ee3024df81ef304917d941ca1f0ef77e81608c3d444ce9dd7 +size 2377930688 diff --git a/GrayLine-Gemma3-4B.Q5_K_M.gguf b/GrayLine-Gemma3-4B.Q5_K_M.gguf new file mode 100644 index 0000000..6ab4f6f --- /dev/null +++ b/GrayLine-Gemma3-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f473e13a7c578973e24b18bfe7f86cb70f40e25b756a3dc4e3fc63f46879ce2 +size 2829699008 diff --git a/GrayLine-Gemma3-4B.Q5_K_S.gguf b/GrayLine-Gemma3-4B.Q5_K_S.gguf new file mode 100644 index 0000000..1072058 --- /dev/null +++ b/GrayLine-Gemma3-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94cd9782a797f5bd3058372ec1635494d35c6f10158f50672d68c83157f8751c +size 2764593088 diff --git a/GrayLine-Gemma3-4B.Q6_K.gguf b/GrayLine-Gemma3-4B.Q6_K.gguf new file mode 100644 index 0000000..ced56f3 --- /dev/null +++ b/GrayLine-Gemma3-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a4b354a1eb7f272eefa3377b5455aa07c2150af38b32c0859d5173b39a5628d +size 3190740928 diff --git a/GrayLine-Gemma3-4B.Q8_0.gguf b/GrayLine-Gemma3-4B.Q8_0.gguf new file mode 100644 index 0000000..fe98e43 --- /dev/null +++ b/GrayLine-Gemma3-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a4e54b5bc24ef9fb10bf4535d37938aed030fdf90ee7449f6c39329a0eef04 +size 4130403008 diff --git a/GrayLine-Gemma3-4B.f16.gguf b/GrayLine-Gemma3-4B.f16.gguf new file mode 100644 index 0000000..ee1995b --- /dev/null +++ b/GrayLine-Gemma3-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be325584b9c3cf0958b91eab66d4426f03d34f9c85f6ee241df85c8056d361cf +size 7767804608 diff --git a/GrayLine-Gemma3-4B.mmproj-Q8_0.gguf b/GrayLine-Gemma3-4B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..f98936c --- /dev/null +++ b/GrayLine-Gemma3-4B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec105f8635400193a7241defcf14f91509d99d0469816db9b8300f0a161106f5 +size 591378208 diff --git a/GrayLine-Gemma3-4B.mmproj-f16.gguf b/GrayLine-Gemma3-4B.mmproj-f16.gguf new file mode 100644 index 0000000..113390d --- /dev/null +++ b/GrayLine-Gemma3-4B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83985e49f868d671b06788d1ddc6463803769de1d5d750fe66c4f1379a04be77 +size 851252128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d7220cc --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: soob3123/GrayLine-Gemma3-4B +datasets: +- soob3123/GrayLine-QA +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- uncensored +- direct-answer +- information-retrieval +- general-knowledge +- unfiltered +- amoral-ai +--- +## About + + + + + + +static quants of https://huggingface.co/soob3123/GrayLine-Gemma3-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GrayLine-Gemma3-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-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/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GrayLine-Gemma3-4B-GGUF/resolve/main/GrayLine-Gemma3-4B.f16.gguf) | f16 | 7.9 | 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. + +