commit 39f7c52963f5394e36dafb3ffe287d6f0eef5b09 Author: ModelHub XC Date: Wed Apr 22 04:26:49 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinySwallow-1.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..44a1ca3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +TinySwallow-1.5B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinySwallow-1.5B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinySwallow-1.5B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinySwallow-1.5B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinySwallow-1.5B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinySwallow-1.5B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinySwallow-1.5B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinySwallow-1.5B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinySwallow-1.5B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinySwallow-1.5B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinySwallow-1.5B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinySwallow-1.5B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9e93579 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: SakanaAI/TinySwallow-1.5B-Instruct +datasets: +- tokyotech-llm/lmsys-chat-1m-synth +- tokyotech-llm/swallow-magpie-ultra-v0.1 +- tokyotech-llm/swallow-swallow-gemma-magpie-v0.1 +language: +- ja +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/SakanaAI/TinySwallow-1.5B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TinySwallow-1.5B-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/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinySwallow-1.5B-Instruct-GGUF/resolve/main/TinySwallow-1.5B-Instruct.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/TinySwallow-1.5B-Instruct.IQ4_XS.gguf b/TinySwallow-1.5B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..aec6c33 --- /dev/null +++ b/TinySwallow-1.5B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a4edc6fe84d34cf45c5810d325862732f531f4343f480bac1b214b71a42c555 +size 902184256 diff --git a/TinySwallow-1.5B-Instruct.Q2_K.gguf b/TinySwallow-1.5B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..64dbcd0 --- /dev/null +++ b/TinySwallow-1.5B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5df9531920161ae3fe5b028447c641c5d208623566044e5ac3ac9eea19a1b120 +size 676306240 diff --git a/TinySwallow-1.5B-Instruct.Q3_K_L.gguf b/TinySwallow-1.5B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..09d1c74 --- /dev/null +++ b/TinySwallow-1.5B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a229353dd4330f121d796fa4e4cf80f91a30923b0a3cd38bd34b0aaaf5d6fea +size 880164160 diff --git a/TinySwallow-1.5B-Instruct.Q3_K_M.gguf b/TinySwallow-1.5B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b96a8cd --- /dev/null +++ b/TinySwallow-1.5B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6eaf0f057d3d611109b853bff5dcdc5cc673af8488eda0aee8be6b9276a1b9a +size 824180032 diff --git a/TinySwallow-1.5B-Instruct.Q3_K_S.gguf b/TinySwallow-1.5B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..d531666 --- /dev/null +++ b/TinySwallow-1.5B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7625fe2d04600e182aa5fc0f641fd50c01f3422a73f0f21682af3ef7019e185 +size 760945984 diff --git a/TinySwallow-1.5B-Instruct.Q4_K_M.gguf b/TinySwallow-1.5B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..3460011 --- /dev/null +++ b/TinySwallow-1.5B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ba182ac25a5c502f7579dd8fbc954216ab57b20b56f44e23578cdb0716e9f6 +size 986049856 diff --git a/TinySwallow-1.5B-Instruct.Q4_K_S.gguf b/TinySwallow-1.5B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..c2864c1 --- /dev/null +++ b/TinySwallow-1.5B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e99c72210c84790a812ea5d29a56613ba91d5fad1d3e15504e273de1245b6a08 +size 940313920 diff --git a/TinySwallow-1.5B-Instruct.Q5_K_M.gguf b/TinySwallow-1.5B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..fc70b49 --- /dev/null +++ b/TinySwallow-1.5B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8216a082c662c591efb52dd605f6394327a65f617e011ea95798b4ee8fe2572 +size 1125051712 diff --git a/TinySwallow-1.5B-Instruct.Q5_K_S.gguf b/TinySwallow-1.5B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..96e9baf --- /dev/null +++ b/TinySwallow-1.5B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dba7eadb19725eec0c15d3d1bba87ce001bd87b038c35d8db5b74968844fdb93 +size 1098730816 diff --git a/TinySwallow-1.5B-Instruct.Q6_K.gguf b/TinySwallow-1.5B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..4650e4e --- /dev/null +++ b/TinySwallow-1.5B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:865fd82bd24f31fda24bf910fbe5723f44f674c3ab4a07d79535dd3ea1d6ea1c +size 1272741184 diff --git a/TinySwallow-1.5B-Instruct.Q8_0.gguf b/TinySwallow-1.5B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..3ca5914 --- /dev/null +++ b/TinySwallow-1.5B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c08ad09da77604223625c5dfd328c56c2a1e096f22c719635627b3b51f89e2d3 +size 1646574400 diff --git a/TinySwallow-1.5B-Instruct.f16.gguf b/TinySwallow-1.5B-Instruct.f16.gguf new file mode 100644 index 0000000..6e68a21 --- /dev/null +++ b/TinySwallow-1.5B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:616fd252d1add70857bc5645859f4fe97dcc0c1a571b79d8381458deb88c3cc2 +size 3093670720