commit 55aaf345486abb88f41cb1d6b033ee90e9a6929a Author: ModelHub XC Date: Tue May 26 06:35:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OctoThinker-3B-Short-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..77c1eca --- /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 +OctoThinker-3B-Short-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Short-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OctoThinker-3B-Short-Base.IQ4_XS.gguf b/OctoThinker-3B-Short-Base.IQ4_XS.gguf new file mode 100644 index 0000000..8d77bd8 --- /dev/null +++ b/OctoThinker-3B-Short-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9456bdd7ee6a8f008635703abce3980f56d7b77f7726c20a7525f76486a0029f +size 1840903776 diff --git a/OctoThinker-3B-Short-Base.Q2_K.gguf b/OctoThinker-3B-Short-Base.Q2_K.gguf new file mode 100644 index 0000000..85ee761 --- /dev/null +++ b/OctoThinker-3B-Short-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b00c740baac0bcdb30f1e3e2e2420ba0b5501b3db4a3f55d2a37dab399030d9 +size 1363932768 diff --git a/OctoThinker-3B-Short-Base.Q3_K_L.gguf b/OctoThinker-3B-Short-Base.Q3_K_L.gguf new file mode 100644 index 0000000..1fa36c2 --- /dev/null +++ b/OctoThinker-3B-Short-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:134a6ed86d721512acd48a597394426a8420f3ebce17a5050597a2b7023bc18f +size 1815344736 diff --git a/OctoThinker-3B-Short-Base.Q3_K_M.gguf b/OctoThinker-3B-Short-Base.Q3_K_M.gguf new file mode 100644 index 0000000..f6a6471 --- /dev/null +++ b/OctoThinker-3B-Short-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99bedecb7130c2fd80af1a7bfc1f133127ce6aa97831a96efd1cefd8d970726b +size 1687156320 diff --git a/OctoThinker-3B-Short-Base.Q3_K_S.gguf b/OctoThinker-3B-Short-Base.Q3_K_S.gguf new file mode 100644 index 0000000..8236821 --- /dev/null +++ b/OctoThinker-3B-Short-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0de21bc246745858ba60736791f789c1724e8d4a23e4d4d5cba23e8e69696792 +size 1542846048 diff --git a/OctoThinker-3B-Short-Base.Q4_K_M.gguf b/OctoThinker-3B-Short-Base.Q4_K_M.gguf new file mode 100644 index 0000000..940d651 --- /dev/null +++ b/OctoThinker-3B-Short-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e93a832c19d3b8d4193a57e9d45c9fb3e2e054c9aa5c708c81fa365517aa48c +size 2019374688 diff --git a/OctoThinker-3B-Short-Base.Q4_K_S.gguf b/OctoThinker-3B-Short-Base.Q4_K_S.gguf new file mode 100644 index 0000000..0457d64 --- /dev/null +++ b/OctoThinker-3B-Short-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125e73aeb9547a55e32701b0de0592d0a2307e3364bdca7dc3eb51454563a0ad +size 1928197728 diff --git a/OctoThinker-3B-Short-Base.Q5_K_M.gguf b/OctoThinker-3B-Short-Base.Q5_K_M.gguf new file mode 100644 index 0000000..e7b9262 --- /dev/null +++ b/OctoThinker-3B-Short-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16a2c457ac0d4ef7c432a5de0ff252ee5baec79a9893251a9538213b29bfb12c +size 2322151008 diff --git a/OctoThinker-3B-Short-Base.Q5_K_S.gguf b/OctoThinker-3B-Short-Base.Q5_K_S.gguf new file mode 100644 index 0000000..dbd1004 --- /dev/null +++ b/OctoThinker-3B-Short-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:981752e8af5431f4073941befd6bbdc5f4f0a55ec71fa0c0becfb374d8e9990e +size 2269509216 diff --git a/OctoThinker-3B-Short-Base.Q6_K.gguf b/OctoThinker-3B-Short-Base.Q6_K.gguf new file mode 100644 index 0000000..90ae77d --- /dev/null +++ b/OctoThinker-3B-Short-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d1ff26d1c11a76f83007ae298ca2e67e7df64bbad98178f1d5f54ba3eac990 +size 2643850848 diff --git a/OctoThinker-3B-Short-Base.Q8_0.gguf b/OctoThinker-3B-Short-Base.Q8_0.gguf new file mode 100644 index 0000000..3bb9234 --- /dev/null +++ b/OctoThinker-3B-Short-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3dac4df54099bacbf4e4965d98df708e3094c9cfb11a01c933d531c570b09ef +size 3421896288 diff --git a/OctoThinker-3B-Short-Base.f16.gguf b/OctoThinker-3B-Short-Base.f16.gguf new file mode 100644 index 0000000..4e49c52 --- /dev/null +++ b/OctoThinker-3B-Short-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7e6c72aaec7b6a5bcf76b5247d75e32238c1f7bf0d0bfd0fd718f1a9f375892 +size 6433685088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0147446 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: OctoThinker/OctoThinker-3B-Short-Base +datasets: +- OctoThinker/MegaMath-Web-Pro-Max +- LLM360/MegaMath +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/OctoThinker/OctoThinker-3B-Short-Base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OctoThinker-3B-Short-Base-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-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/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Short-Base-GGUF/resolve/main/OctoThinker-3B-Short-Base.f16.gguf) | f16 | 6.5 | 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. + +