commit 4b6a70d8e087beff29dd1d14ff041ffda5a95b85 Author: ModelHub XC Date: Tue Apr 21 20:24:31 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MiniThinky-1B-Llama-3.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2d24cf3 --- /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 +MiniThinky-1B-Llama-3.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MiniThinky-1B-Llama-3.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniThinky-1B-Llama-3.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MiniThinky-1B-Llama-3.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniThinky-1B-Llama-3.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniThinky-1B-Llama-3.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniThinky-1B-Llama-3.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniThinky-1B-Llama-3.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniThinky-1B-Llama-3.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniThinky-1B-Llama-3.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniThinky-1B-Llama-3.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MiniThinky-1B-Llama-3.2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MiniThinky-1B-Llama-3.2.IQ4_XS.gguf b/MiniThinky-1B-Llama-3.2.IQ4_XS.gguf new file mode 100644 index 0000000..83cbe88 --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051bad71f93f767f8e794bdcbe334f72404c86deb0c673a6fbc93b4d50086dc6 +size 748384928 diff --git a/MiniThinky-1B-Llama-3.2.Q2_K.gguf b/MiniThinky-1B-Llama-3.2.Q2_K.gguf new file mode 100644 index 0000000..ead9323 --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4134a0cedc328d4277fe56c1db38e75f467e235995ec6c8d676aa26e166aba90 +size 580874912 diff --git a/MiniThinky-1B-Llama-3.2.Q3_K_L.gguf b/MiniThinky-1B-Llama-3.2.Q3_K_L.gguf new file mode 100644 index 0000000..96fbe5e --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591cedbf5d02f6886b34ffc9e09cb1952e93cd36954ddcb9e62432fac67a85b0 +size 732525216 diff --git a/MiniThinky-1B-Llama-3.2.Q3_K_M.gguf b/MiniThinky-1B-Llama-3.2.Q3_K_M.gguf new file mode 100644 index 0000000..4768edc --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b92eed970eed946d888a3d59e4391be2cc63bc03c58b75b18613bf5030819658 +size 690844320 diff --git a/MiniThinky-1B-Llama-3.2.Q3_K_S.gguf b/MiniThinky-1B-Llama-3.2.Q3_K_S.gguf new file mode 100644 index 0000000..e049bfb --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ffa2d2eadae51c00a5226724ee56e9595eab5fb1a796e8f202b1ea825152a5b +size 641692320 diff --git a/MiniThinky-1B-Llama-3.2.Q4_K_M.gguf b/MiniThinky-1B-Llama-3.2.Q4_K_M.gguf new file mode 100644 index 0000000..0b3bc4c --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53524e6c2debb84f1a9e8141bcc96025d4c86108322a194b75b68ea5d721a74e +size 807695008 diff --git a/MiniThinky-1B-Llama-3.2.Q4_K_S.gguf b/MiniThinky-1B-Llama-3.2.Q4_K_S.gguf new file mode 100644 index 0000000..262ae23 --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca0e51df504c364b8e0cfc261795e311ea357468cadd4929e14ded87c496e60 +size 775647904 diff --git a/MiniThinky-1B-Llama-3.2.Q5_K_M.gguf b/MiniThinky-1B-Llama-3.2.Q5_K_M.gguf new file mode 100644 index 0000000..9eb3973 --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1f975c537e751c41db99eb27df85857940f592321483c84c67dc78c2861d245 +size 911504032 diff --git a/MiniThinky-1B-Llama-3.2.Q5_K_S.gguf b/MiniThinky-1B-Llama-3.2.Q5_K_S.gguf new file mode 100644 index 0000000..9e2b911 --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ba5070562c35980e03721bc4053dcba2c1200c1a0c1fb60be19778f6f0ab23 +size 892564128 diff --git a/MiniThinky-1B-Llama-3.2.Q6_K.gguf b/MiniThinky-1B-Llama-3.2.Q6_K.gguf new file mode 100644 index 0000000..8268b30 --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2098f05ae44b5994568a1bdabf79a4f1c10cad31c5a451e52d582f798f681f3e +size 1021801120 diff --git a/MiniThinky-1B-Llama-3.2.Q8_0.gguf b/MiniThinky-1B-Llama-3.2.Q8_0.gguf new file mode 100644 index 0000000..5bea62f --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3358d23cffabedf5059e5c31ea4c5028e266de7cc6781e91450d0351e595c79 +size 1321083552 diff --git a/MiniThinky-1B-Llama-3.2.f16.gguf b/MiniThinky-1B-Llama-3.2.f16.gguf new file mode 100644 index 0000000..2b871dc --- /dev/null +++ b/MiniThinky-1B-Llama-3.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80bb8fed821edc7267159753711d59280686446d9ea1818049d38d50de3d5d36 +size 2479596192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a02d01a --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: ngxson/MiniThinky-1B-Llama-3.2 +datasets: +- ngxson/MiniThinky-dataset +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/ngxson/MiniThinky-1B-Llama-3.2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-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/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MiniThinky-1B-Llama-3.2-GGUF/resolve/main/MiniThinky-1B-Llama-3.2.f16.gguf) | f16 | 2.6 | 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. + +