commit de7daa0ad44d22ac31c9bd26b2692bd57cb9310a Author: ModelHub XC Date: Wed Apr 22 09:11:51 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Saba1.5-Pro-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3a7ab8f --- /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 +Saba1.5-Pro.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.f16.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Saba1.5-Pro.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..2b3222b --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Sakalti/Saba1.5-Pro +datasets: +- HuggingFaceH4/ultrachat_200k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Sakalti/Saba1.5-Pro + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Saba1.5-Pro-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/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Saba1.5-Pro-GGUF/resolve/main/Saba1.5-Pro.f16.gguf) | f16 | 3.2 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/Saba1.5-Pro.IQ4_XS.gguf b/Saba1.5-Pro.IQ4_XS.gguf new file mode 100644 index 0000000..dc26524 --- /dev/null +++ b/Saba1.5-Pro.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4249335727d4693aa6cd789f5aa09c4ed50dd61c65f17ee37148d23404ad20b4 +size 902183360 diff --git a/Saba1.5-Pro.Q2_K.gguf b/Saba1.5-Pro.Q2_K.gguf new file mode 100644 index 0000000..6e99707 --- /dev/null +++ b/Saba1.5-Pro.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7560935b6a34ac506303bcd511218e09963365fdea1a80c9b945253e10e727bf +size 676305344 diff --git a/Saba1.5-Pro.Q3_K_L.gguf b/Saba1.5-Pro.Q3_K_L.gguf new file mode 100644 index 0000000..7422297 --- /dev/null +++ b/Saba1.5-Pro.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0415b16e60edd2ca576eaae90f6c8d9466bf91a8944ff88de034b75bda355f4 +size 880163264 diff --git a/Saba1.5-Pro.Q3_K_M.gguf b/Saba1.5-Pro.Q3_K_M.gguf new file mode 100644 index 0000000..7fa36b2 --- /dev/null +++ b/Saba1.5-Pro.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35dd95ac374db229f7907abf7c63954c2b430ff6ad542c80f78e68f1f8ae23b0 +size 824179136 diff --git a/Saba1.5-Pro.Q3_K_S.gguf b/Saba1.5-Pro.Q3_K_S.gguf new file mode 100644 index 0000000..bd19c9a --- /dev/null +++ b/Saba1.5-Pro.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5447f6b61061d4992978d43fc15789bcf1ac4849a4d4194999f6edbdf8e9a9c0 +size 760945088 diff --git a/Saba1.5-Pro.Q4_0_4_4.gguf b/Saba1.5-Pro.Q4_0_4_4.gguf new file mode 100644 index 0000000..c72a78c --- /dev/null +++ b/Saba1.5-Pro.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d94a15b5ff019a8d682eb0134c0595478d0be4040450fe8b88fc0b599cc1065d +size 934955456 diff --git a/Saba1.5-Pro.Q4_K_M.gguf b/Saba1.5-Pro.Q4_K_M.gguf new file mode 100644 index 0000000..9e85b39 --- /dev/null +++ b/Saba1.5-Pro.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0cee7778087b01f7549569f1efd1c3dbfe839d573fd548a950855164cc2b720 +size 986048960 diff --git a/Saba1.5-Pro.Q4_K_S.gguf b/Saba1.5-Pro.Q4_K_S.gguf new file mode 100644 index 0000000..80b938c --- /dev/null +++ b/Saba1.5-Pro.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0189eb27955cc3fa13be52228f4066c9c8fc1dad613c90140ff8b4c11321befb +size 940313024 diff --git a/Saba1.5-Pro.Q5_K_M.gguf b/Saba1.5-Pro.Q5_K_M.gguf new file mode 100644 index 0000000..4ac11d0 --- /dev/null +++ b/Saba1.5-Pro.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2324a260bdf0fdb50c79ad4ee106b6e4b02dfa43d3ecd01657a55ee9a21e89b9 +size 1125050816 diff --git a/Saba1.5-Pro.Q5_K_S.gguf b/Saba1.5-Pro.Q5_K_S.gguf new file mode 100644 index 0000000..1a5f3a2 --- /dev/null +++ b/Saba1.5-Pro.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8adec8114ba4bd488d774fd4c451c82fe0ea1b3a6cfd8cde3e61f60aae2b11 +size 1098729920 diff --git a/Saba1.5-Pro.Q6_K.gguf b/Saba1.5-Pro.Q6_K.gguf new file mode 100644 index 0000000..4950395 --- /dev/null +++ b/Saba1.5-Pro.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a419309aab229860e9bf2905d2115c42d0a59857272ed71f2221bb4a48584b +size 1272740288 diff --git a/Saba1.5-Pro.Q8_0.gguf b/Saba1.5-Pro.Q8_0.gguf new file mode 100644 index 0000000..f1aed22 --- /dev/null +++ b/Saba1.5-Pro.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa04efe63af991f13684202393d0a510799505eb7b67699c708c4d48ba64d3c1 +size 1646573504 diff --git a/Saba1.5-Pro.f16.gguf b/Saba1.5-Pro.f16.gguf new file mode 100644 index 0000000..df18a04 --- /dev/null +++ b/Saba1.5-Pro.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00de20e96e22e6ffa8341d0b6108062102fb60e57dd3ed5ca98980ee7073c2d6 +size 3093669824