commit f87aa206fe4e0e31cf3f11f0b8374d9629b5a453 Author: ModelHub XC Date: Thu May 7 00:43:49 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MicroThinker-8B-Preview-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fbe7b88 --- /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 +MicroThinker-8B-Preview.f16.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-8B-Preview.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-8B-Preview.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-8B-Preview.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-8B-Preview.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-8B-Preview.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-8B-Preview.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-8B-Preview.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-8B-Preview.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-8B-Preview.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-8B-Preview.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MicroThinker-8B-Preview.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MicroThinker-8B-Preview.IQ4_XS.gguf b/MicroThinker-8B-Preview.IQ4_XS.gguf new file mode 100644 index 0000000..5c1d802 --- /dev/null +++ b/MicroThinker-8B-Preview.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691765ebb9bfb6984786f02f44f8499ea2a18de660b240d40a5867575fc7a980 +size 4484368416 diff --git a/MicroThinker-8B-Preview.Q2_K.gguf b/MicroThinker-8B-Preview.Q2_K.gguf new file mode 100644 index 0000000..ff42597 --- /dev/null +++ b/MicroThinker-8B-Preview.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e443518ea705af6eae340510ca5ff4327dd204280cab8bf8ccc15abcf6f9bacb +size 3179137056 diff --git a/MicroThinker-8B-Preview.Q3_K_L.gguf b/MicroThinker-8B-Preview.Q3_K_L.gguf new file mode 100644 index 0000000..28e3c94 --- /dev/null +++ b/MicroThinker-8B-Preview.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c92b8a8de4918853b42abb3144d0603955c76821d086e4a107f72d9fe0fbba6 +size 4321962016 diff --git a/MicroThinker-8B-Preview.Q3_K_M.gguf b/MicroThinker-8B-Preview.Q3_K_M.gguf new file mode 100644 index 0000000..31bc216 --- /dev/null +++ b/MicroThinker-8B-Preview.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f33e3cb757832ad27302fc912f994ba4b21cde48f99da90301fc764dc2cd1b2 +size 4018923552 diff --git a/MicroThinker-8B-Preview.Q3_K_S.gguf b/MicroThinker-8B-Preview.Q3_K_S.gguf new file mode 100644 index 0000000..48e6fe7 --- /dev/null +++ b/MicroThinker-8B-Preview.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf96f071b3cfcaf4d64d739cc448a2a7fb2bb8c1395d937b39fcf4d7f4420068 +size 3664504864 diff --git a/MicroThinker-8B-Preview.Q4_K_M.gguf b/MicroThinker-8B-Preview.Q4_K_M.gguf new file mode 100644 index 0000000..115caf6 --- /dev/null +++ b/MicroThinker-8B-Preview.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f215439c9ba694d4b29febd9ae23179930244c344b29ea2657fdc64770cfdd9 +size 4920739872 diff --git a/MicroThinker-8B-Preview.Q4_K_S.gguf b/MicroThinker-8B-Preview.Q4_K_S.gguf new file mode 100644 index 0000000..b9d8c06 --- /dev/null +++ b/MicroThinker-8B-Preview.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4fc384d3b3c142c56b9c0af93d14885ac16abce48b79a86a50a0be54b426a82 +size 4692674592 diff --git a/MicroThinker-8B-Preview.Q5_K_M.gguf b/MicroThinker-8B-Preview.Q5_K_M.gguf new file mode 100644 index 0000000..be0930a --- /dev/null +++ b/MicroThinker-8B-Preview.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60c1fed448583209cce650695bbca823b761e00863e58ebfe760367b934c88c3 +size 5732993056 diff --git a/MicroThinker-8B-Preview.Q5_K_S.gguf b/MicroThinker-8B-Preview.Q5_K_S.gguf new file mode 100644 index 0000000..38d8b61 --- /dev/null +++ b/MicroThinker-8B-Preview.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96b00b4305b00e4ca7ded75f3b23c620c3c5d3f6c40ed2804b057b5a7923208d +size 5599299616 diff --git a/MicroThinker-8B-Preview.Q6_K.gguf b/MicroThinker-8B-Preview.Q6_K.gguf new file mode 100644 index 0000000..6b51133 --- /dev/null +++ b/MicroThinker-8B-Preview.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d5dd53c0a95b2731a74a6e8db56258603c7ec7aa90ff1337533aca82bfbd89d +size 6596012064 diff --git a/MicroThinker-8B-Preview.Q8_0.gguf b/MicroThinker-8B-Preview.Q8_0.gguf new file mode 100644 index 0000000..9612a6f --- /dev/null +++ b/MicroThinker-8B-Preview.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a862768582944295ad85ad16058112ef395c80de9e8c1427d221c61cf06dea21 +size 8540776480 diff --git a/MicroThinker-8B-Preview.f16.gguf b/MicroThinker-8B-Preview.f16.gguf new file mode 100644 index 0000000..c868ec2 --- /dev/null +++ b/MicroThinker-8B-Preview.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6179c4468e123b307577c0c554f90836338d4237311572748218dc0cd8d84d8b +size 16068896800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fdb0cdb --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: huihui-ai/MicroThinker-8B-Preview +datasets: +- huihui-ai/FineQwQ-142k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- llama3.1 +--- +## About + + + + + + +static quants of https://huggingface.co/huihui-ai/MicroThinker-8B-Preview + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MicroThinker-8B-Preview-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/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MicroThinker-8B-Preview-GGUF/resolve/main/MicroThinker-8B-Preview.f16.gguf) | f16 | 16.2 | 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. + +