commit bb3421e0192d38ccf1df58a156e082941d386a42 Author: ModelHub XC Date: Mon Aug 24 19:57:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ff38da7 --- /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 +Entropy-Llama-3.2-3B-Instruct-MATH.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Entropy-Llama-3.2-3B-Instruct-MATH.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Entropy-Llama-3.2-3B-Instruct-MATH.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Entropy-Llama-3.2-3B-Instruct-MATH.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Entropy-Llama-3.2-3B-Instruct-MATH.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Entropy-Llama-3.2-3B-Instruct-MATH.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Entropy-Llama-3.2-3B-Instruct-MATH.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Entropy-Llama-3.2-3B-Instruct-MATH.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Entropy-Llama-3.2-3B-Instruct-MATH.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.IQ4_XS.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.IQ4_XS.gguf new file mode 100644 index 0000000..c553528 --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c3a10d6328a55eb6d42feb570cf53badde81d8811e1e53142bbe53377fb9d7 +size 2050220800 diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.Q2_K.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.Q2_K.gguf new file mode 100644 index 0000000..6241d17 --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ca495d496a2210245c3b64a2bdcb44aff68c62a76adfcd8345919e05fb021e7 +size 1493218048 diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_L.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_L.gguf new file mode 100644 index 0000000..c27d9c4 --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c9a575e91a6170810cffbf4ca70013acadb5610821b2adb59d0b7e7a94a7004 +size 1984645888 diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_M.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_M.gguf new file mode 100644 index 0000000..cd9ec85 --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a907ac27eb0f8999bd2a691ce5630a9eee14ba288157c800c6bb02dfd9cb683 +size 1856457472 diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_S.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_S.gguf new file mode 100644 index 0000000..d4205a2 --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419d4dd864b6151c5d24d76a4d5c27e53737345ba11b90da786c00eb4c76954b +size 1712147200 diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.Q4_K_M.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.Q4_K_M.gguf new file mode 100644 index 0000000..062a645 --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4fb0e1b574652e2facb2492f05226f5a33915c64c52a22b0e0065f7da3d9a5e +size 2241004288 diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.Q4_K_S.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.Q4_K_S.gguf new file mode 100644 index 0000000..3bd3e6a --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42ba6b2a712f0fd79bdedded4ee8b11597c6d44c8e1b5944827cfbf76d40c27c +size 2149827328 diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.Q5_K_M.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.Q5_K_M.gguf new file mode 100644 index 0000000..b7fe65f --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f090a5d89022f34bb9ed6e34752c5fd4e7904c05fbe8e516e3268b42c3d9a4a0 +size 2593030912 diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.Q5_K_S.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.Q5_K_S.gguf new file mode 100644 index 0000000..1a5e380 --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a816f0dbfd7ae468e986c5a1d643abcaf9f8c6d515908fcfcc143cbb836af5 +size 2540389120 diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.Q6_K.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.Q6_K.gguf new file mode 100644 index 0000000..b79b77a --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acf804a2c91bb9e930fa528ec69df5318c767cba4e4c6383b3e7dea1dd3dd9a2 +size 2967059200 diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.Q8_0.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.Q8_0.gguf new file mode 100644 index 0000000..9c4f55f --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10a460d5528b53084327b114670681a672b6d6c4f05718744948188687ea786f +size 3840527104 diff --git a/Entropy-Llama-3.2-3B-Instruct-MATH.f16.gguf b/Entropy-Llama-3.2-3B-Instruct-MATH.f16.gguf new file mode 100644 index 0000000..1dc7718 --- /dev/null +++ b/Entropy-Llama-3.2-3B-Instruct-MATH.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a1361f21d59a70b93b21e4f7d7c704f3af2baec48fc808423616facb1454c7a +size 7221693184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8eaa8c4 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: TMLR-Group-HF/Entropy-Llama-3.2-3B-Instruct-MATH +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/TMLR-Group-HF/Entropy-Llama-3.2-3B-Instruct-MATH + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Entropy-Llama-3.2-3B-Instruct-MATH-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Entropy-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Entropy-Llama-3.2-3B-Instruct-MATH.f16.gguf) | f16 | 7.3 | 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. + +