commit 41550ace0774aeb64e259437b245399a46ade06a Author: ModelHub XC Date: Fri Sep 4 01:43:32 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2c1c227 --- /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 +Thinker-SmolLM2-135M-Instruct-Reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Thinker-SmolLM2-135M-Instruct-Reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Thinker-SmolLM2-135M-Instruct-Reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Thinker-SmolLM2-135M-Instruct-Reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Thinker-SmolLM2-135M-Instruct-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Thinker-SmolLM2-135M-Instruct-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Thinker-SmolLM2-135M-Instruct-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Thinker-SmolLM2-135M-Instruct-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Thinker-SmolLM2-135M-Instruct-Reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2c33e3c --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: ewre324/ewre324-Thinker-SmolLM2-135M-Instruct-Reasoning +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- safetensors +- onnx +- transformers.js +--- +## About + + + + + + +static quants of https://huggingface.co/ewre324/ewre324-Thinker-SmolLM2-135M-Instruct-Reasoning + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-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/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Thinker-SmolLM2-135M-Instruct-Reasoning-GGUF/resolve/main/Thinker-SmolLM2-135M-Instruct-Reasoning.f16.gguf) | f16 | 0.4 | 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/Thinker-SmolLM2-135M-Instruct-Reasoning.IQ4_XS.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..8a498aa --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1966b0fa584c1f772d811bf0873111ecbf94668f80b36ad7a537ca127974710d +size 91313152 diff --git a/Thinker-SmolLM2-135M-Instruct-Reasoning.Q2_K.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q2_K.gguf new file mode 100644 index 0000000..b8e49c3 --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f856fe1c9d8ea03904901abb204d0273feec045e36ec894240f9ee07ae13f73 +size 88202752 diff --git a/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_L.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..aaddc75 --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ccfd82aa4fcff8a056eea41acf62dfa68a73d4666d031b7fcd9c00a4f5f20b8 +size 97533952 diff --git a/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_M.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..f8136bb --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1cae30df10d7b25374d003b0204014317d5613e5acce2b6b638c8f0c5098bfb +size 93511168 diff --git a/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_S.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..ad25790 --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f007072eabad9a20401ce040fe0ae46ac32b7c1de3d809db2576c1141dfa53 +size 88202752 diff --git a/Thinker-SmolLM2-135M-Instruct-Reasoning.Q4_K_M.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..e8d5b09 --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59daf1b68a1267146df418553a12e81ad5189e5c0bbff367331ce7d6610cca71 +size 105455104 diff --git a/Thinker-SmolLM2-135M-Instruct-Reasoning.Q4_K_S.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..37c1444 --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3880cb9ac4747245b028c4eed7d6b40b921ac19be9064449c90f5e9458341be6 +size 102040576 diff --git a/Thinker-SmolLM2-135M-Instruct-Reasoning.Q5_K_M.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..807f50b --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9218928ce1918d6dfe4807df96ba673a75780e65bb89ea81f359329f99498bda +size 112104448 diff --git a/Thinker-SmolLM2-135M-Instruct-Reasoning.Q5_K_S.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..72d3653 --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f237bff4f9e0fd8dc8eaa81d8cc9980abf1d83a9556630b8d9a8e280e89154b3 +size 109975552 diff --git a/Thinker-SmolLM2-135M-Instruct-Reasoning.Q6_K.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..b1b1fe5 --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ad5617f225d1f987d06499bd71f4a6edd89717fb3f30b0b09bd17e5d3a7793e +size 138383872 diff --git a/Thinker-SmolLM2-135M-Instruct-Reasoning.Q8_0.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..43321f5 --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6157dcde3b310e1285a25311937c501106876ae817d4c67441b861696ac2cd8 +size 144812032 diff --git a/Thinker-SmolLM2-135M-Instruct-Reasoning.f16.gguf b/Thinker-SmolLM2-135M-Instruct-Reasoning.f16.gguf new file mode 100644 index 0000000..546770c --- /dev/null +++ b/Thinker-SmolLM2-135M-Instruct-Reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22d4af4089fc021025c6b965e303e6a551e34d6a5734a2fc47d8b785c29c3cb +size 270886912