From f837624b1d2ec6f2a7a510e52dc8ed445fe873d0 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 26 May 2026 16:22:17 +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/hotshot-thinking-v1-4b-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++++++++++++ README.md | 71 ++++++++++++++++++++++++++++++ hotshot-thinking-v1-4b.IQ4_XS.gguf | 3 ++ hotshot-thinking-v1-4b.Q2_K.gguf | 3 ++ hotshot-thinking-v1-4b.Q3_K_L.gguf | 3 ++ hotshot-thinking-v1-4b.Q3_K_M.gguf | 3 ++ hotshot-thinking-v1-4b.Q3_K_S.gguf | 3 ++ hotshot-thinking-v1-4b.Q4_K_M.gguf | 3 ++ hotshot-thinking-v1-4b.Q4_K_S.gguf | 3 ++ hotshot-thinking-v1-4b.Q5_K_M.gguf | 3 ++ hotshot-thinking-v1-4b.Q5_K_S.gguf | 3 ++ hotshot-thinking-v1-4b.Q6_K.gguf | 3 ++ hotshot-thinking-v1-4b.Q8_0.gguf | 3 ++ hotshot-thinking-v1-4b.f16.gguf | 3 ++ 14 files changed, 154 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 hotshot-thinking-v1-4b.IQ4_XS.gguf create mode 100644 hotshot-thinking-v1-4b.Q2_K.gguf create mode 100644 hotshot-thinking-v1-4b.Q3_K_L.gguf create mode 100644 hotshot-thinking-v1-4b.Q3_K_M.gguf create mode 100644 hotshot-thinking-v1-4b.Q3_K_S.gguf create mode 100644 hotshot-thinking-v1-4b.Q4_K_M.gguf create mode 100644 hotshot-thinking-v1-4b.Q4_K_S.gguf create mode 100644 hotshot-thinking-v1-4b.Q5_K_M.gguf create mode 100644 hotshot-thinking-v1-4b.Q5_K_S.gguf create mode 100644 hotshot-thinking-v1-4b.Q6_K.gguf create mode 100644 hotshot-thinking-v1-4b.Q8_0.gguf create mode 100644 hotshot-thinking-v1-4b.f16.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eca0caa --- /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 +hotshot-thinking-v1-4b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +hotshot-thinking-v1-4b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +hotshot-thinking-v1-4b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +hotshot-thinking-v1-4b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hotshot-thinking-v1-4b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +hotshot-thinking-v1-4b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hotshot-thinking-v1-4b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +hotshot-thinking-v1-4b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hotshot-thinking-v1-4b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +hotshot-thinking-v1-4b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +hotshot-thinking-v1-4b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +hotshot-thinking-v1-4b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5eb73b2 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: czlonkowski/hotshot-thinking-v1-4b +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/czlonkowski/hotshot-thinking-v1-4b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#hotshot-thinking-v1-4b-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/hotshot-thinking-v1-4b-GGUF/resolve/main/hotshot-thinking-v1-4b.f16.gguf) | f16 | 8.2 | 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. + + diff --git a/hotshot-thinking-v1-4b.IQ4_XS.gguf b/hotshot-thinking-v1-4b.IQ4_XS.gguf new file mode 100644 index 0000000..f41682a --- /dev/null +++ b/hotshot-thinking-v1-4b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d995ccb9c34202746fdde244de0c49e8793e552ee1f9d3fb9bfde861e7c09d0 +size 2286316096 diff --git a/hotshot-thinking-v1-4b.Q2_K.gguf b/hotshot-thinking-v1-4b.Q2_K.gguf new file mode 100644 index 0000000..307e808 --- /dev/null +++ b/hotshot-thinking-v1-4b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17294a639250f2f02a9b365d9b334eb3a7fba38e7d8a8b20496c8956c6f70b19 +size 1669499456 diff --git a/hotshot-thinking-v1-4b.Q3_K_L.gguf b/hotshot-thinking-v1-4b.Q3_K_L.gguf new file mode 100644 index 0000000..9ea15a9 --- /dev/null +++ b/hotshot-thinking-v1-4b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e97f0b41b8e610643472d6f2cbba54f7f625b44e9b130182e6ce02a3599778 +size 2239785536 diff --git a/hotshot-thinking-v1-4b.Q3_K_M.gguf b/hotshot-thinking-v1-4b.Q3_K_M.gguf new file mode 100644 index 0000000..43dd632 --- /dev/null +++ b/hotshot-thinking-v1-4b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a5ec67737a94ab9fca07a9e03353101704a099f93b391b9c770873eae6cd0f7 +size 2075617856 diff --git a/hotshot-thinking-v1-4b.Q3_K_S.gguf b/hotshot-thinking-v1-4b.Q3_K_S.gguf new file mode 100644 index 0000000..78239ad --- /dev/null +++ b/hotshot-thinking-v1-4b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a52845936ec4a393e339788dfd792e95757a67e4e051ccaf4ba185af12e4350 +size 1886997056 diff --git a/hotshot-thinking-v1-4b.Q4_K_M.gguf b/hotshot-thinking-v1-4b.Q4_K_M.gguf new file mode 100644 index 0000000..518ddc7 --- /dev/null +++ b/hotshot-thinking-v1-4b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa2c07a3e4507c920939b35a7de94a8a0072698a34c68c9696de7074a959dd5c +size 2497280576 diff --git a/hotshot-thinking-v1-4b.Q4_K_S.gguf b/hotshot-thinking-v1-4b.Q4_K_S.gguf new file mode 100644 index 0000000..1a65af3 --- /dev/null +++ b/hotshot-thinking-v1-4b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a71c15f3e708f9f2b15e03b3ae5e8a41b3dd5f47b5853efb7fc49442f35302b6 +size 2383309376 diff --git a/hotshot-thinking-v1-4b.Q5_K_M.gguf b/hotshot-thinking-v1-4b.Q5_K_M.gguf new file mode 100644 index 0000000..c87ee91 --- /dev/null +++ b/hotshot-thinking-v1-4b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15ce2bed36097611fb27309f0d6e4f6c2dad69a5881ab156e3da5f634568bb78 +size 2889513536 diff --git a/hotshot-thinking-v1-4b.Q5_K_S.gguf b/hotshot-thinking-v1-4b.Q5_K_S.gguf new file mode 100644 index 0000000..30af68c --- /dev/null +++ b/hotshot-thinking-v1-4b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d675b74689991980edb23b221dbc7266c3c692323e37b1aa3a76a1f6ecd8dd0 +size 2823711296 diff --git a/hotshot-thinking-v1-4b.Q6_K.gguf b/hotshot-thinking-v1-4b.Q6_K.gguf new file mode 100644 index 0000000..f431701 --- /dev/null +++ b/hotshot-thinking-v1-4b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d05008be546c459709757381769fd9176c58710340248d9ad6280af7fe1d653 +size 3306261056 diff --git a/hotshot-thinking-v1-4b.Q8_0.gguf b/hotshot-thinking-v1-4b.Q8_0.gguf new file mode 100644 index 0000000..8654495 --- /dev/null +++ b/hotshot-thinking-v1-4b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eb9a3f9ae398dd9681b7806872e120dfd374195fce1e6cb47961674be5af499 +size 4280405056 diff --git a/hotshot-thinking-v1-4b.f16.gguf b/hotshot-thinking-v1-4b.f16.gguf new file mode 100644 index 0000000..0dad9a9 --- /dev/null +++ b/hotshot-thinking-v1-4b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9932c044afbe130f04ac0f1c2a5662348dd0342588fd982de95927d552268dee +size 8051285056