commit ee799b8fbb95a1ce80d9de91bd969406611050e7 Author: ModelHub XC Date: Mon May 25 10:43:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-ProXMath-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f6e4517 --- /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 +TinyLlama-1.1B-ProXMath.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-ProXMath.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-ProXMath.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-ProXMath.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-ProXMath.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-ProXMath.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-ProXMath.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-ProXMath.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-ProXMath.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-ProXMath.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-ProXMath.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-ProXMath.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d6c9927 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: gair-prox/TinyLlama-1.1B-ProXMath +datasets: +- gair-prox/open-web-math-pro +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/gair-prox/TinyLlama-1.1B-ProXMath + + +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/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-ProXMath-GGUF/resolve/main/TinyLlama-1.1B-ProXMath.f16.gguf) | f16 | 2.3 | 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. + + diff --git a/TinyLlama-1.1B-ProXMath.IQ4_XS.gguf b/TinyLlama-1.1B-ProXMath.IQ4_XS.gguf new file mode 100644 index 0000000..8c84372 --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da0246e23bfdc1f1db4e84b2655b4d3d59811ca7458b6c821425d2d051fc89c +size 609808288 diff --git a/TinyLlama-1.1B-ProXMath.Q2_K.gguf b/TinyLlama-1.1B-ProXMath.Q2_K.gguf new file mode 100644 index 0000000..db3f344 --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e63c352069b326de7ba1242cc81438bff7296831bc107fce7e8d1cfb0520a9 +size 432132000 diff --git a/TinyLlama-1.1B-ProXMath.Q3_K_L.gguf b/TinyLlama-1.1B-ProXMath.Q3_K_L.gguf new file mode 100644 index 0000000..0e93a87 --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d55c1da8641365e603e6d52a2983375ab4fc5be8a763ca718de6b20b2c12cad1 +size 591527840 diff --git a/TinyLlama-1.1B-ProXMath.Q3_K_M.gguf b/TinyLlama-1.1B-ProXMath.Q3_K_M.gguf new file mode 100644 index 0000000..3db8885 --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72fde9276c098fe6351e6bd65f4a8d5612d4deaf1bede332b295f115423032f6 +size 548405152 diff --git a/TinyLlama-1.1B-ProXMath.Q3_K_S.gguf b/TinyLlama-1.1B-ProXMath.Q3_K_S.gguf new file mode 100644 index 0000000..b7c4063 --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2679df24ae193c488fc69398160675d69ed4fa3cb41f9ff0f92367881511b8d2 +size 499343264 diff --git a/TinyLlama-1.1B-ProXMath.Q4_K_M.gguf b/TinyLlama-1.1B-ProXMath.Q4_K_M.gguf new file mode 100644 index 0000000..d4bcb48 --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e82f26d9d829ee0310de6b28a58a7a2a82b15d375908b788108975791b8ced1 +size 667815840 diff --git a/TinyLlama-1.1B-ProXMath.Q4_K_S.gguf b/TinyLlama-1.1B-ProXMath.Q4_K_S.gguf new file mode 100644 index 0000000..540babe --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6331bf91087d36cd4b957d633e11ea5ba618f58be638f1843eec02b5272de5a0 +size 639872928 diff --git a/TinyLlama-1.1B-ProXMath.Q5_K_M.gguf b/TinyLlama-1.1B-ProXMath.Q5_K_M.gguf new file mode 100644 index 0000000..21ffcf3 --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d3ca079501122aa5fbe61332fe7f73731a0d36b3980c5f20f9716e554798c81 +size 782045088 diff --git a/TinyLlama-1.1B-ProXMath.Q5_K_S.gguf b/TinyLlama-1.1B-ProXMath.Q5_K_S.gguf new file mode 100644 index 0000000..699f7f2 --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82ad0885fa005adf212a9f64904c6bf956cb5f365424fa4b31a38aa58ca764c4 +size 766029728 diff --git a/TinyLlama-1.1B-ProXMath.Q6_K.gguf b/TinyLlama-1.1B-ProXMath.Q6_K.gguf new file mode 100644 index 0000000..c764618 --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f832581c4378237bc5dab8dab6cd02d9f274c061d4a9a287cb8f938a1df29677 +size 903413664 diff --git a/TinyLlama-1.1B-ProXMath.Q8_0.gguf b/TinyLlama-1.1B-ProXMath.Q8_0.gguf new file mode 100644 index 0000000..7163e6e --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:503385b9fa448aab58d345cc5bb11072b8023054571b49f07e7e106e962bd071 +size 1169809312 diff --git a/TinyLlama-1.1B-ProXMath.f16.gguf b/TinyLlama-1.1B-ProXMath.f16.gguf new file mode 100644 index 0000000..7fa8917 --- /dev/null +++ b/TinyLlama-1.1B-ProXMath.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d30c29095967c24470e84a5e393293502fc148c6776ebf746eb72f8e27217a6 +size 2201018272