commit 8abfea1bb097edd272f6dcbd6029a8816f6b06f3 Author: ModelHub XC Date: Fri May 1 05:01:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Express.1-Math-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..60b994a --- /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 +Llama-Express.1-Math.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Math.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Math.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Math.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Math.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Math.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Math.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Math.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Math.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Math.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Math.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Math.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Express.1-Math.IQ4_XS.gguf b/Llama-Express.1-Math.IQ4_XS.gguf new file mode 100644 index 0000000..4f92891 --- /dev/null +++ b/Llama-Express.1-Math.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d45cb2936f1ddae5a33bfad9539b6732e6916f85224d833aa8fd7e0fc6b741 +size 748385600 diff --git a/Llama-Express.1-Math.Q2_K.gguf b/Llama-Express.1-Math.Q2_K.gguf new file mode 100644 index 0000000..487244d --- /dev/null +++ b/Llama-Express.1-Math.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0b2544a2dd7877a49e685de3f01a857551cb4e43a92102d8a241107a398fef0 +size 580875584 diff --git a/Llama-Express.1-Math.Q3_K_L.gguf b/Llama-Express.1-Math.Q3_K_L.gguf new file mode 100644 index 0000000..34cc646 --- /dev/null +++ b/Llama-Express.1-Math.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7d90dc293b1f7d4c0e947242ac5c6e2133195540e3693cb64947013e6a53251 +size 732525888 diff --git a/Llama-Express.1-Math.Q3_K_M.gguf b/Llama-Express.1-Math.Q3_K_M.gguf new file mode 100644 index 0000000..9bf3bf3 --- /dev/null +++ b/Llama-Express.1-Math.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3373bdd86d0b3480747fd49cba8c556ef9ecc9b8ce643a5ed05fc044f97a80bd +size 690844992 diff --git a/Llama-Express.1-Math.Q3_K_S.gguf b/Llama-Express.1-Math.Q3_K_S.gguf new file mode 100644 index 0000000..5ae0f5d --- /dev/null +++ b/Llama-Express.1-Math.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e936a21fa59830023d81bec34093cceb3e63bb475723cb4adbb1c8f64ea3ff3 +size 641692992 diff --git a/Llama-Express.1-Math.Q4_K_M.gguf b/Llama-Express.1-Math.Q4_K_M.gguf new file mode 100644 index 0000000..9da8439 --- /dev/null +++ b/Llama-Express.1-Math.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a71efe0bec740183719bc48c3f59c7177f62d2ac7ecd6c07002e53ee63d66f36 +size 807695680 diff --git a/Llama-Express.1-Math.Q4_K_S.gguf b/Llama-Express.1-Math.Q4_K_S.gguf new file mode 100644 index 0000000..8a2e4f7 --- /dev/null +++ b/Llama-Express.1-Math.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6846789d8d6e77d3627a11d9565e5eec11b64b8805b95d92d1d09b5f5a133ef9 +size 775648576 diff --git a/Llama-Express.1-Math.Q5_K_M.gguf b/Llama-Express.1-Math.Q5_K_M.gguf new file mode 100644 index 0000000..7011a27 --- /dev/null +++ b/Llama-Express.1-Math.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0defd87b06450328d92d807825dd53fa58b7db6b1f55a439b07671f3fd4edcf +size 911504704 diff --git a/Llama-Express.1-Math.Q5_K_S.gguf b/Llama-Express.1-Math.Q5_K_S.gguf new file mode 100644 index 0000000..5d8d38d --- /dev/null +++ b/Llama-Express.1-Math.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78dccdeca597157c8aab8d03932520189caed087dca3b3a638c5ddc6c10ecfe +size 892564800 diff --git a/Llama-Express.1-Math.Q6_K.gguf b/Llama-Express.1-Math.Q6_K.gguf new file mode 100644 index 0000000..0b06378 --- /dev/null +++ b/Llama-Express.1-Math.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5187ead0229f71c4264ca6c6ecd1e62b7d55019eb042075339155b53c60f7ecb +size 1021801792 diff --git a/Llama-Express.1-Math.Q8_0.gguf b/Llama-Express.1-Math.Q8_0.gguf new file mode 100644 index 0000000..31c8793 --- /dev/null +++ b/Llama-Express.1-Math.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee3de02f677b385838b0e389b0013714876f9b58a9362cdf26f0045a0b8257e +size 1321084224 diff --git a/Llama-Express.1-Math.f16.gguf b/Llama-Express.1-Math.f16.gguf new file mode 100644 index 0000000..d224dfc --- /dev/null +++ b/Llama-Express.1-Math.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b11a7415179aa6f155f21cf1badc5e5a75f849191a60d1449a3ea3a3c202f4 +size 2479596864 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ea1c8af --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: prithivMLmods/Llama-Express.1-Math +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +tags: +- express +- math +- llama3.2 +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Llama-Express.1-Math + + +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/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Math-GGUF/resolve/main/Llama-Express.1-Math.f16.gguf) | f16 | 2.6 | 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. + +