commit f3c2378114897c4e5659b4682fe5b8d8e7fc52b1 Author: ModelHub XC Date: Thu Jul 2 02:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MegaMath-Llama-3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3c6c125 --- /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 +MegaMath-Llama-3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MegaMath-Llama-3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MegaMath-Llama-3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MegaMath-Llama-3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaMath-Llama-3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MegaMath-Llama-3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaMath-Llama-3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MegaMath-Llama-3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaMath-Llama-3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MegaMath-Llama-3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MegaMath-Llama-3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MegaMath-Llama-3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MegaMath-Llama-3.2-3B.IQ4_XS.gguf b/MegaMath-Llama-3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..cad5fc5 --- /dev/null +++ b/MegaMath-Llama-3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c08cbfd387789b6de5889419c6eca926d13f4a684d59783e4390c976a8fa86e +size 1840903296 diff --git a/MegaMath-Llama-3.2-3B.Q2_K.gguf b/MegaMath-Llama-3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..81642b1 --- /dev/null +++ b/MegaMath-Llama-3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd185c63780789a68e93365e5d6f01148a5f80eabb3a635bc46c19148e8ce652 +size 1363932288 diff --git a/MegaMath-Llama-3.2-3B.Q3_K_L.gguf b/MegaMath-Llama-3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..e7e0ff8 --- /dev/null +++ b/MegaMath-Llama-3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64f7dc1dce551474a2ac381f65c2b508aa08a4577ec9309d1350c108423b3dac +size 1815344256 diff --git a/MegaMath-Llama-3.2-3B.Q3_K_M.gguf b/MegaMath-Llama-3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..b7b036b --- /dev/null +++ b/MegaMath-Llama-3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2761ef586d4bc151afbf5707479c9a66e77767e5e2a81c62353fd44f520cf160 +size 1687155840 diff --git a/MegaMath-Llama-3.2-3B.Q3_K_S.gguf b/MegaMath-Llama-3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..0cebe70 --- /dev/null +++ b/MegaMath-Llama-3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff9e7fc57ec86ffa628fc8df954ec816f4f2deebbbf1aa3287206ef0b8ddbf46 +size 1542845568 diff --git a/MegaMath-Llama-3.2-3B.Q4_K_M.gguf b/MegaMath-Llama-3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..1ab5426 --- /dev/null +++ b/MegaMath-Llama-3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b25afff35c1c94928135419f6ea84d5aff537fa7f99cb9e09aac9eefdbb54a4 +size 2019374208 diff --git a/MegaMath-Llama-3.2-3B.Q4_K_S.gguf b/MegaMath-Llama-3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..35d4a2a --- /dev/null +++ b/MegaMath-Llama-3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c53b381770e17f3d022bb8974be0ba7aff79fe209c59acbb9776cfa67ad769 +size 1928197248 diff --git a/MegaMath-Llama-3.2-3B.Q5_K_M.gguf b/MegaMath-Llama-3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..8a5cdd1 --- /dev/null +++ b/MegaMath-Llama-3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71dfe61d00a08679d0effa23a771701e59f2abc63ef6c2879930e3eee1ce5668 +size 2322150528 diff --git a/MegaMath-Llama-3.2-3B.Q5_K_S.gguf b/MegaMath-Llama-3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..be70986 --- /dev/null +++ b/MegaMath-Llama-3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e02a15711db6093d7c79869d914088f93d0c0d6d13eb61d524aef2b0f0f804 +size 2269508736 diff --git a/MegaMath-Llama-3.2-3B.Q6_K.gguf b/MegaMath-Llama-3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..7ac7cf7 --- /dev/null +++ b/MegaMath-Llama-3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f32ccac08ed334beb36a0aa739b543648ad0bb225f2a53c93d8aacf6dacc8a04 +size 2643850368 diff --git a/MegaMath-Llama-3.2-3B.Q8_0.gguf b/MegaMath-Llama-3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..eedb1d8 --- /dev/null +++ b/MegaMath-Llama-3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6770bdb314953033cfead1e81183dbf29da35c686c593f340ac60f0f57c76de +size 3421895808 diff --git a/MegaMath-Llama-3.2-3B.f16.gguf b/MegaMath-Llama-3.2-3B.f16.gguf new file mode 100644 index 0000000..36c2c43 --- /dev/null +++ b/MegaMath-Llama-3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:907d391584df467cd27ff282f52c22866af23652b006115ed83f46971e3d7247 +size 6433684608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7393b70 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Soheilmaker/MegaMath-Llama-3.2-3B +datasets: +- LLM360/MegaMath +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- math +- code +- cot +- pal +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Soheilmaker/MegaMath-Llama-3.2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MegaMath-Llama-3.2-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-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/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MegaMath-Llama-3.2-3B-GGUF/resolve/main/MegaMath-Llama-3.2-3B.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. + +