commit c2bcb9b73c7a37ded36582d994cfa57a609a820b Author: ModelHub XC Date: Thu Jun 4 03:30:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/InftyThink-1.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e2dafb3 --- /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 +InftyThink-1.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +InftyThink-1.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +InftyThink-1.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +InftyThink-1.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InftyThink-1.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InftyThink-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InftyThink-1.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InftyThink-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InftyThink-1.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InftyThink-1.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +InftyThink-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InftyThink-1.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/InftyThink-1.5B.IQ4_XS.gguf b/InftyThink-1.5B.IQ4_XS.gguf new file mode 100644 index 0000000..f80f890 --- /dev/null +++ b/InftyThink-1.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2ea5fa27558ab2179174c9f30d1bed4ddf8a604d6f39caa4a063285ccd83455 +size 1026162464 diff --git a/InftyThink-1.5B.Q2_K.gguf b/InftyThink-1.5B.Q2_K.gguf new file mode 100644 index 0000000..f40131d --- /dev/null +++ b/InftyThink-1.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b18f98a6a2cad4428246b12a3c3f4abfc37f1aa19bd71d6746cdf796d08e630d +size 752880416 diff --git a/InftyThink-1.5B.Q3_K_L.gguf b/InftyThink-1.5B.Q3_K_L.gguf new file mode 100644 index 0000000..0b2e116 --- /dev/null +++ b/InftyThink-1.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:720b50bb47c5c53990f51ae91d7ec481795bedf28e0d0898a3084a27340240e9 +size 980440352 diff --git a/InftyThink-1.5B.Q3_K_M.gguf b/InftyThink-1.5B.Q3_K_M.gguf new file mode 100644 index 0000000..e1c4453 --- /dev/null +++ b/InftyThink-1.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e22e5bccedb0015a8be07fe0d14ca66d5602ce5a394e1c6e39b50c30b28e19e +size 924456224 diff --git a/InftyThink-1.5B.Q3_K_S.gguf b/InftyThink-1.5B.Q3_K_S.gguf new file mode 100644 index 0000000..42d2090 --- /dev/null +++ b/InftyThink-1.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52955e28e602f0630fe2f6a1ef9eaa6503a897567f5b6be1c9ea54746acd124d +size 861222176 diff --git a/InftyThink-1.5B.Q4_K_M.gguf b/InftyThink-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..ce4a01f --- /dev/null +++ b/InftyThink-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d5e49632d49447c3254e0851cff10f1d9aab32efcd3b6aa08d727eb92098d0 +size 1117320992 diff --git a/InftyThink-1.5B.Q4_K_S.gguf b/InftyThink-1.5B.Q4_K_S.gguf new file mode 100644 index 0000000..ce2d189 --- /dev/null +++ b/InftyThink-1.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b0920d7e12c53746e28988570173004861445e7aece3f207fcfab01c85d14e +size 1071585056 diff --git a/InftyThink-1.5B.Q5_K_M.gguf b/InftyThink-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..0f90fd5 --- /dev/null +++ b/InftyThink-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c2fec702c711c98cfbd4cfb8f8aaa9ed5574f7fddc2850f758c15a38a070a9 +size 1285494560 diff --git a/InftyThink-1.5B.Q5_K_S.gguf b/InftyThink-1.5B.Q5_K_S.gguf new file mode 100644 index 0000000..5436aab --- /dev/null +++ b/InftyThink-1.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1604f168b2e79d4ba18f92e5433bbd34bda362be84bafa9dfa746911dd5d8355 +size 1259173664 diff --git a/InftyThink-1.5B.Q6_K.gguf b/InftyThink-1.5B.Q6_K.gguf new file mode 100644 index 0000000..5245c7b --- /dev/null +++ b/InftyThink-1.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:093cd50ac9985e8c77b8f8118c8c00cb182ee2333eaa6b8ec4768d167a5bd1ed +size 1464178976 diff --git a/InftyThink-1.5B.Q8_0.gguf b/InftyThink-1.5B.Q8_0.gguf new file mode 100644 index 0000000..9615d58 --- /dev/null +++ b/InftyThink-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3f05637254c399aef09974feb3590b3d617814d6aa9776bc9089e77c41fc019 +size 1894532384 diff --git a/InftyThink-1.5B.f16.gguf b/InftyThink-1.5B.f16.gguf new file mode 100644 index 0000000..6137f20 --- /dev/null +++ b/InftyThink-1.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19c80c3af95033d5afb15a5ec6fec495b0491ba1ec38afea4e4350dd5366745d +size 3560416544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e86283e --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: yanyc/InftyThink-1.5B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/yanyc/InftyThink-1.5B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InftyThink-1.5B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/InftyThink-1.5B-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/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/InftyThink-1.5B-GGUF/resolve/main/InftyThink-1.5B.f16.gguf) | f16 | 3.7 | 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. + +