From 7ed51b9baeba5cd3ba412fc297b28c088bb4ed57 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 12 Sep 2026 14:28:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/samantha-1.1-westlake-7b-GGUF Source: Original Platform --- .gitattributes | 48 +++++++++++++++++ README.md | 72 ++++++++++++++++++++++++++ samantha-1.1-westlake-7b.IQ4_XS.gguf | 3 ++ samantha-1.1-westlake-7b.Q2_K.gguf | 3 ++ samantha-1.1-westlake-7b.Q3_K_L.gguf | 3 ++ samantha-1.1-westlake-7b.Q3_K_M.gguf | 3 ++ samantha-1.1-westlake-7b.Q3_K_S.gguf | 3 ++ samantha-1.1-westlake-7b.Q4_0_4_4.gguf | 3 ++ samantha-1.1-westlake-7b.Q4_K_M.gguf | 3 ++ samantha-1.1-westlake-7b.Q4_K_S.gguf | 3 ++ samantha-1.1-westlake-7b.Q5_K_M.gguf | 3 ++ samantha-1.1-westlake-7b.Q5_K_S.gguf | 3 ++ samantha-1.1-westlake-7b.Q6_K.gguf | 3 ++ samantha-1.1-westlake-7b.Q8_0.gguf | 3 ++ samantha-1.1-westlake-7b.f16.gguf | 3 ++ 15 files changed, 159 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 samantha-1.1-westlake-7b.IQ4_XS.gguf create mode 100644 samantha-1.1-westlake-7b.Q2_K.gguf create mode 100644 samantha-1.1-westlake-7b.Q3_K_L.gguf create mode 100644 samantha-1.1-westlake-7b.Q3_K_M.gguf create mode 100644 samantha-1.1-westlake-7b.Q3_K_S.gguf create mode 100644 samantha-1.1-westlake-7b.Q4_0_4_4.gguf create mode 100644 samantha-1.1-westlake-7b.Q4_K_M.gguf create mode 100644 samantha-1.1-westlake-7b.Q4_K_S.gguf create mode 100644 samantha-1.1-westlake-7b.Q5_K_M.gguf create mode 100644 samantha-1.1-westlake-7b.Q5_K_S.gguf create mode 100644 samantha-1.1-westlake-7b.Q6_K.gguf create mode 100644 samantha-1.1-westlake-7b.Q8_0.gguf create mode 100644 samantha-1.1-westlake-7b.f16.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52574a3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +samantha-1.1-westlake-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.1-westlake-7b.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d93cc6f --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: QuixiAI/samantha-1.1-westlake-7b +datasets: +- cognitivecomputations/samantha-data +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/QuixiAI/samantha-1.1-westlake-7b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#samantha-1.1-westlake-7b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-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/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/samantha-1.1-westlake-7b-GGUF/resolve/main/samantha-1.1-westlake-7b.f16.gguf) | f16 | 14.6 | 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/samantha-1.1-westlake-7b.IQ4_XS.gguf b/samantha-1.1-westlake-7b.IQ4_XS.gguf new file mode 100644 index 0000000..3a4693d --- /dev/null +++ b/samantha-1.1-westlake-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e948bf60fab9b4abe5fb004c2671848637ff00f95ff092884b6f3fbd98ef8782 +size 3944400832 diff --git a/samantha-1.1-westlake-7b.Q2_K.gguf b/samantha-1.1-westlake-7b.Q2_K.gguf new file mode 100644 index 0000000..ff23438 --- /dev/null +++ b/samantha-1.1-westlake-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25bd8afcd4ec8ad35e79642b7ed02ca1d0ffdd440992c32f80da2f6e0c6f95d3 +size 2719252800 diff --git a/samantha-1.1-westlake-7b.Q3_K_L.gguf b/samantha-1.1-westlake-7b.Q3_K_L.gguf new file mode 100644 index 0000000..1adfc91 --- /dev/null +++ b/samantha-1.1-westlake-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b95772460efe661f5082901cbbfe9082e68804ff80e4e57eab189237cf60c43 +size 3822036096 diff --git a/samantha-1.1-westlake-7b.Q3_K_M.gguf b/samantha-1.1-westlake-7b.Q3_K_M.gguf new file mode 100644 index 0000000..522b321 --- /dev/null +++ b/samantha-1.1-westlake-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d789e751b38b217112ba6ad119b4a793ee1a219ba7489a9d4f5b142e5d1482cc +size 3518997632 diff --git a/samantha-1.1-westlake-7b.Q3_K_S.gguf b/samantha-1.1-westlake-7b.Q3_K_S.gguf new file mode 100644 index 0000000..0d069b4 --- /dev/null +++ b/samantha-1.1-westlake-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1241257bb16e2ac44f17105daddf05f1d1473c089c3c009c94c62115f10aba08 +size 3164578944 diff --git a/samantha-1.1-westlake-7b.Q4_0_4_4.gguf b/samantha-1.1-westlake-7b.Q4_0_4_4.gguf new file mode 100644 index 0000000..c2d1ae2 --- /dev/null +++ b/samantha-1.1-westlake-7b.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:032e5f4412b324d760da4a866056d8bd8932b95d2513650fe5309c7b305fc08d +size 4108929216 diff --git a/samantha-1.1-westlake-7b.Q4_K_M.gguf b/samantha-1.1-westlake-7b.Q4_K_M.gguf new file mode 100644 index 0000000..258d401 --- /dev/null +++ b/samantha-1.1-westlake-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cfa29d4a97c6018e4af579f2a6ee619943af0964a18dc7e158c97351a865856 +size 4368451776 diff --git a/samantha-1.1-westlake-7b.Q4_K_S.gguf b/samantha-1.1-westlake-7b.Q4_K_S.gguf new file mode 100644 index 0000000..f1dfd1e --- /dev/null +++ b/samantha-1.1-westlake-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cdd886d9a04b02dc8f33fff4cd1d0ea72696d1e8ab27ec7fe4e4e3f20935c6e +size 4140386496 diff --git a/samantha-1.1-westlake-7b.Q5_K_M.gguf b/samantha-1.1-westlake-7b.Q5_K_M.gguf new file mode 100644 index 0000000..f2215c3 --- /dev/null +++ b/samantha-1.1-westlake-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07005da61c3d402c008c28cae977f8cce3e882c0194bfee546cc8ca3440d2659 +size 5131422912 diff --git a/samantha-1.1-westlake-7b.Q5_K_S.gguf b/samantha-1.1-westlake-7b.Q5_K_S.gguf new file mode 100644 index 0000000..47983e5 --- /dev/null +++ b/samantha-1.1-westlake-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b46601595db181f4fb6540a51e14d2094924f805e6635ea76a1d314951fef74 +size 4997729472 diff --git a/samantha-1.1-westlake-7b.Q6_K.gguf b/samantha-1.1-westlake-7b.Q6_K.gguf new file mode 100644 index 0000000..28af5ce --- /dev/null +++ b/samantha-1.1-westlake-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ca2331581bc3208eaed4a3d04d217296ff1f5adcb331939f7f8181c72946165 +size 5942079744 diff --git a/samantha-1.1-westlake-7b.Q8_0.gguf b/samantha-1.1-westlake-7b.Q8_0.gguf new file mode 100644 index 0000000..faa838f --- /dev/null +++ b/samantha-1.1-westlake-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9226725b81f94793aa0c418557179cd17a2edb1c74b1373cbe6da894a6452b87 +size 7695876224 diff --git a/samantha-1.1-westlake-7b.f16.gguf b/samantha-1.1-westlake-7b.f16.gguf new file mode 100644 index 0000000..ecda204 --- /dev/null +++ b/samantha-1.1-westlake-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfc9e283c40869865d9e00b02e660ec057477ab86b4bb0e6137332f2d943a034 +size 14484765824