commit 0e11088629e88cc8343761842a21b56cf474eee2 Author: ModelHub XC Date: Thu May 14 02:49:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-3-4b-document-writer-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..43d1b14 --- /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 +gemma-3-4b-document-writer.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-document-writer.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4b918ad --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: ZySec-AI/gemma-3-4b-document-writer +datasets: +- ZySec-AI/contexual-rewriter-dataset +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- rag +- security +- legal +- ai4good +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ZySec-AI/gemma-3-4b-document-writer + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-3-4b-document-writer-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-3-4b-document-writer-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/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-document-writer-GGUF/resolve/main/gemma-3-4b-document-writer.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. + + diff --git a/gemma-3-4b-document-writer.IQ4_XS.gguf b/gemma-3-4b-document-writer.IQ4_XS.gguf new file mode 100644 index 0000000..7470ef6 --- /dev/null +++ b/gemma-3-4b-document-writer.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e810f8f48af9a450d8d902e864994fb59c330feea206848f5d0b2648c39fa0dc +size 2279626720 diff --git a/gemma-3-4b-document-writer.Q2_K.gguf b/gemma-3-4b-document-writer.Q2_K.gguf new file mode 100644 index 0000000..566c410 --- /dev/null +++ b/gemma-3-4b-document-writer.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:044a99cd9b1d8061241ce00754858c232bc44a2f53c8f8d2e443780fbe2e2a27 +size 1729165280 diff --git a/gemma-3-4b-document-writer.Q3_K_L.gguf b/gemma-3-4b-document-writer.Q3_K_L.gguf new file mode 100644 index 0000000..218de66 --- /dev/null +++ b/gemma-3-4b-document-writer.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3194cc12d92652d8c2dd0c8d0ff58bdf144569eb14c97a7ce8be7ee48cdeb03 +size 2236086240 diff --git a/gemma-3-4b-document-writer.Q3_K_M.gguf b/gemma-3-4b-document-writer.Q3_K_M.gguf new file mode 100644 index 0000000..1184b96 --- /dev/null +++ b/gemma-3-4b-document-writer.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bed2479191621183f7e1f1fd147b3d2845916fd279fdfc64a90d91b37f37aad9 +size 2098460640 diff --git a/gemma-3-4b-document-writer.Q3_K_S.gguf b/gemma-3-4b-document-writer.Q3_K_S.gguf new file mode 100644 index 0000000..78719ce --- /dev/null +++ b/gemma-3-4b-document-writer.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:669f7f47d4455c58cb908d0bc2d424fbb0b31ed7c4eeeaa50e894d0b7e4cf2ee +size 1937364960 diff --git a/gemma-3-4b-document-writer.Q4_K_M.gguf b/gemma-3-4b-document-writer.Q4_K_M.gguf new file mode 100644 index 0000000..e67d08a --- /dev/null +++ b/gemma-3-4b-document-writer.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47f808e1c07b70c0a458c5118b6a73d8171a24f304abbf784874daa1f1e363e4 +size 2489894880 diff --git a/gemma-3-4b-document-writer.Q4_K_S.gguf b/gemma-3-4b-document-writer.Q4_K_S.gguf new file mode 100644 index 0000000..e26b6cf --- /dev/null +++ b/gemma-3-4b-document-writer.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd54f4b7a5c8d754a79c3ce35c374a31ebc84d34ff434bba2351774329a1ee9 +size 2377930720 diff --git a/gemma-3-4b-document-writer.Q5_K_M.gguf b/gemma-3-4b-document-writer.Q5_K_M.gguf new file mode 100644 index 0000000..3ab2dbb --- /dev/null +++ b/gemma-3-4b-document-writer.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ce233e65c7af50f920df1383a6d3554d9ffe800e4bca5c42ebca7de92cd436 +size 2829699040 diff --git a/gemma-3-4b-document-writer.Q5_K_S.gguf b/gemma-3-4b-document-writer.Q5_K_S.gguf new file mode 100644 index 0000000..7945eef --- /dev/null +++ b/gemma-3-4b-document-writer.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a608dac2b2405499633a0905954b6dbaa903de638c98fd7799511fe3e78b43a7 +size 2764593120 diff --git a/gemma-3-4b-document-writer.Q6_K.gguf b/gemma-3-4b-document-writer.Q6_K.gguf new file mode 100644 index 0000000..7729821 --- /dev/null +++ b/gemma-3-4b-document-writer.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bb855de418c7857ddfb019404d6a0c2ea24e98904dfb9db73162ea349bd7467 +size 3190740960 diff --git a/gemma-3-4b-document-writer.Q8_0.gguf b/gemma-3-4b-document-writer.Q8_0.gguf new file mode 100644 index 0000000..500dee5 --- /dev/null +++ b/gemma-3-4b-document-writer.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3e209bb6861596ab2f5856938d3c594bac60af6655d6db9eae2f0cbd2b0c0ea +size 4130403040 diff --git a/gemma-3-4b-document-writer.f16.gguf b/gemma-3-4b-document-writer.f16.gguf new file mode 100644 index 0000000..dd34f32 --- /dev/null +++ b/gemma-3-4b-document-writer.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e384b33d70f942d36bf7aa00dba11cc64c5fee3db53491c49a3ddf956b975de6 +size 7767804640 diff --git a/gemma-3-4b-document-writer.mmproj-Q8_0.gguf b/gemma-3-4b-document-writer.mmproj-Q8_0.gguf new file mode 100644 index 0000000..340c2a9 --- /dev/null +++ b/gemma-3-4b-document-writer.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e636e44cc283d0781233e35301d410d886ecefa6a6c65667662081fefc40be +size 591378144 diff --git a/gemma-3-4b-document-writer.mmproj-f16.gguf b/gemma-3-4b-document-writer.mmproj-f16.gguf new file mode 100644 index 0000000..72118d0 --- /dev/null +++ b/gemma-3-4b-document-writer.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ded3a196a76fdfe9d2e8c8f92d90a9f56c1313d3861d4b440ce662bdfe50c58 +size 851252064