commit 9d290d9753a8ca46133c024f28ddcd6b8d8de509 Author: ModelHub XC Date: Thu Oct 8 22:44:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/sft-math-llama3-8b-base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..51f2176 --- /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 +sft-math-llama3-8b-base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sft-math-llama3-8b-base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +sft-math-llama3-8b-base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-math-llama3-8b-base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +sft-math-llama3-8b-base.f16.gguf filter=lfs diff=lfs merge=lfs -text +sft-math-llama3-8b-base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sft-math-llama3-8b-base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +sft-math-llama3-8b-base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-math-llama3-8b-base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sft-math-llama3-8b-base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-math-llama3-8b-base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +sft-math-llama3-8b-base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..fd21ec5 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: ankner/sft-math-llama3-8b-base +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ankner/sft-math-llama3-8b-base + + +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/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/sft-math-llama3-8b-base-GGUF/resolve/main/sft-math-llama3-8b-base.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. + + diff --git a/sft-math-llama3-8b-base.IQ4_XS.gguf b/sft-math-llama3-8b-base.IQ4_XS.gguf new file mode 100644 index 0000000..888d354 --- /dev/null +++ b/sft-math-llama3-8b-base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389a16a363fee0c37622aa227c7eb8da181a1f2eec5481fd1c78cf6c02a8f5e2 +size 4484363520 diff --git a/sft-math-llama3-8b-base.Q2_K.gguf b/sft-math-llama3-8b-base.Q2_K.gguf new file mode 100644 index 0000000..56f236b --- /dev/null +++ b/sft-math-llama3-8b-base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36d2c7b38c9685e07cc403e967fe353195c2699827042bfd3c09898271ddc10c +size 3179132160 diff --git a/sft-math-llama3-8b-base.Q3_K_L.gguf b/sft-math-llama3-8b-base.Q3_K_L.gguf new file mode 100644 index 0000000..1f3ec72 --- /dev/null +++ b/sft-math-llama3-8b-base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3bbbcd0db2cd3a151ae4ae8a20861dafd80a6b30677c123341339f6032aedd +size 4321957120 diff --git a/sft-math-llama3-8b-base.Q3_K_M.gguf b/sft-math-llama3-8b-base.Q3_K_M.gguf new file mode 100644 index 0000000..df93ea7 --- /dev/null +++ b/sft-math-llama3-8b-base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c225dda77865d516844a32fd58e7bc8330c788ac1a6db3a531b54a3bd31627 +size 4018918656 diff --git a/sft-math-llama3-8b-base.Q3_K_S.gguf b/sft-math-llama3-8b-base.Q3_K_S.gguf new file mode 100644 index 0000000..e42df81 --- /dev/null +++ b/sft-math-llama3-8b-base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c510273529a29ab95187daf3701cc21ffcf5c2d6ad19109a1640b614844b9b2 +size 3664499968 diff --git a/sft-math-llama3-8b-base.Q4_K_M.gguf b/sft-math-llama3-8b-base.Q4_K_M.gguf new file mode 100644 index 0000000..98c7510 --- /dev/null +++ b/sft-math-llama3-8b-base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b098a4535fd70f8cc692e34811e39efc2958ba7e3a666180ede0e71d2f2e2a27 +size 4920734976 diff --git a/sft-math-llama3-8b-base.Q4_K_S.gguf b/sft-math-llama3-8b-base.Q4_K_S.gguf new file mode 100644 index 0000000..6c7b9b2 --- /dev/null +++ b/sft-math-llama3-8b-base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecef62e2a4a8c7f52e4db824cc6856f473ef73e629ee4fc880b992eb6bea5b6c +size 4692669696 diff --git a/sft-math-llama3-8b-base.Q5_K_M.gguf b/sft-math-llama3-8b-base.Q5_K_M.gguf new file mode 100644 index 0000000..a371041 --- /dev/null +++ b/sft-math-llama3-8b-base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:740fd5387fceeb2a85ec0b21585e9b5e8edce8f65282c6223d05caa0f6405f67 +size 5732988160 diff --git a/sft-math-llama3-8b-base.Q5_K_S.gguf b/sft-math-llama3-8b-base.Q5_K_S.gguf new file mode 100644 index 0000000..63a622d --- /dev/null +++ b/sft-math-llama3-8b-base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83887250d1bbe58b36dff5ed14ef1af4777c9baea3599d77d2c5da455ba37515 +size 5599294720 diff --git a/sft-math-llama3-8b-base.Q6_K.gguf b/sft-math-llama3-8b-base.Q6_K.gguf new file mode 100644 index 0000000..79013ff --- /dev/null +++ b/sft-math-llama3-8b-base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2935df490d4718ce8e768c0504f35cd16f506668e2c77996704f2e18d60e248 +size 6596007168 diff --git a/sft-math-llama3-8b-base.Q8_0.gguf b/sft-math-llama3-8b-base.Q8_0.gguf new file mode 100644 index 0000000..adf07c7 --- /dev/null +++ b/sft-math-llama3-8b-base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9005cf475ae008ef2cb49242b9f1c7dc2abc31cfcf8e96f4a2b180fa9a4c636 +size 8540771584 diff --git a/sft-math-llama3-8b-base.f16.gguf b/sft-math-llama3-8b-base.f16.gguf new file mode 100644 index 0000000..9af39bf --- /dev/null +++ b/sft-math-llama3-8b-base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77078849cee30ee0799070fc0bd8e0a58d3329d81755753e92d665fd2a7719b7 +size 16068891904