commit 4b74c418db9428eba9803464e4d9fb412cde71bb Author: ModelHub XC Date: Fri Jun 26 18:31:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MathCoder-Llama3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5bbf41c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +MathCoder-Llama3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder-Llama3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MathCoder-Llama3.1-8B.IQ3_M.gguf b/MathCoder-Llama3.1-8B.IQ3_M.gguf new file mode 100644 index 0000000..6fea13e --- /dev/null +++ b/MathCoder-Llama3.1-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36bf300dbff61e594d276b120239715e14553f2e6b7c22919b74beaf9c73a931 +size 3784824096 diff --git a/MathCoder-Llama3.1-8B.IQ3_S.gguf b/MathCoder-Llama3.1-8B.IQ3_S.gguf new file mode 100644 index 0000000..9e80de7 --- /dev/null +++ b/MathCoder-Llama3.1-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:853f7213b7917b81e9c7110cbae0355ba9e9371c3a6b3d6213559585252a464c +size 3682325792 diff --git a/MathCoder-Llama3.1-8B.IQ3_XS.gguf b/MathCoder-Llama3.1-8B.IQ3_XS.gguf new file mode 100644 index 0000000..5509e3b --- /dev/null +++ b/MathCoder-Llama3.1-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd04278ab3ecc228a2e7052d6422857aaa494c170e61122e4bbac874149357d +size 3518747936 diff --git a/MathCoder-Llama3.1-8B.IQ4_XS.gguf b/MathCoder-Llama3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..c059af8 --- /dev/null +++ b/MathCoder-Llama3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d6d98402e55a9983afbcb53ccccce544974f621f8aa7e3f96d8cff725816967 +size 4484363552 diff --git a/MathCoder-Llama3.1-8B.Q2_K.gguf b/MathCoder-Llama3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..e0bde98 --- /dev/null +++ b/MathCoder-Llama3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e1a5a5608c9a74542821f52c3ba41728ca3263b32a9801be25c48dc06f3a261 +size 3179132192 diff --git a/MathCoder-Llama3.1-8B.Q3_K_L.gguf b/MathCoder-Llama3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..07dbf5f --- /dev/null +++ b/MathCoder-Llama3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6961fced297a3809ce08b5b1b6b5f3788cbd9f9fb738d90fd2d5954a2d79f545 +size 4321957152 diff --git a/MathCoder-Llama3.1-8B.Q3_K_M.gguf b/MathCoder-Llama3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..77a0329 --- /dev/null +++ b/MathCoder-Llama3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:327bce8c6cbeb9069c9f3aff5d0fb5002bbc99d9ea5c3f6ce11473d4ed4ac4b3 +size 4018918688 diff --git a/MathCoder-Llama3.1-8B.Q3_K_S.gguf b/MathCoder-Llama3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..88c2218 --- /dev/null +++ b/MathCoder-Llama3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a546b7a2dcf4829a9b200257088f5a7da1c740bd467635d4167efba9e792c1c1 +size 3664500000 diff --git a/MathCoder-Llama3.1-8B.Q4_K_M.gguf b/MathCoder-Llama3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..cd76116 --- /dev/null +++ b/MathCoder-Llama3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c2bc976a934fe1cfd3d9a44b0f0d5ab66ed19a23c82604af185cec5f9e8d7fc +size 4920735008 diff --git a/MathCoder-Llama3.1-8B.Q4_K_S.gguf b/MathCoder-Llama3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..809c8ca --- /dev/null +++ b/MathCoder-Llama3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc48106dae8423e706b31c584aed47b487390a43456a1e11ce860767ed5fb5d +size 4692669728 diff --git a/MathCoder-Llama3.1-8B.Q5_K_M.gguf b/MathCoder-Llama3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..4833ed6 --- /dev/null +++ b/MathCoder-Llama3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8475e3d0d663a771383cce78d60a461dfa62ec05a780886b252ddc063a6ac199 +size 5732988192 diff --git a/MathCoder-Llama3.1-8B.Q5_K_S.gguf b/MathCoder-Llama3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..2a0881f --- /dev/null +++ b/MathCoder-Llama3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de280ead473036008a40e8d8904c4d25dae3964fd30987e34b4276e9342f60d9 +size 5599294752 diff --git a/MathCoder-Llama3.1-8B.Q6_K.gguf b/MathCoder-Llama3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..f589eb6 --- /dev/null +++ b/MathCoder-Llama3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bec9f9b8d5283d2c030d04d40fda010a5e0a01f473a4ed0b156fd138385ddc51 +size 6596007200 diff --git a/MathCoder-Llama3.1-8B.Q8_0.gguf b/MathCoder-Llama3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..0c6ca71 --- /dev/null +++ b/MathCoder-Llama3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f039e07476bfbd27f42e0186693e3fbc5ec46d6623209839e3ffd616e9ccefd4 +size 8540771616 diff --git a/MathCoder-Llama3.1-8B.f16.gguf b/MathCoder-Llama3.1-8B.f16.gguf new file mode 100644 index 0000000..ec4a1b8 --- /dev/null +++ b/MathCoder-Llama3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b8fd1c1ae59f07c31a84e54481b321dfe1f9805bc0f94a118caa7ef06e2e3eb +size 16068891936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1548435 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: EpistemeAI/MathCoder-Llama3.1-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/EpistemeAI/MathCoder-Llama3.1-8B + + +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/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MathCoder-Llama3.1-8B-GGUF/resolve/main/MathCoder-Llama3.1-8B.f16.gguf) | f16 | 16.2 | 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. + +