commit 3d870eb1420e63de18d87a05035744e6994da54b Author: ModelHub XC Date: Fri Jun 26 02:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/sft-gsm8k-llama3-3b-base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b78cfb9 --- /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-gsm8k-llama3-3b-base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +sft-gsm8k-llama3-3b-base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +sft-gsm8k-llama3-3b-base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +sft-gsm8k-llama3-3b-base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-gsm8k-llama3-3b-base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sft-gsm8k-llama3-3b-base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-gsm8k-llama3-3b-base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sft-gsm8k-llama3-3b-base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-gsm8k-llama3-3b-base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sft-gsm8k-llama3-3b-base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +sft-gsm8k-llama3-3b-base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sft-gsm8k-llama3-3b-base.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..99576da --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: ankner/sft-gsm8k-llama3-3b-base +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ankner/sft-gsm8k-llama3-3b-base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#sft-gsm8k-llama3-3b-base-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/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/sft-gsm8k-llama3-3b-base-GGUF/resolve/main/sft-gsm8k-llama3-3b-base.f16.gguf) | f16 | 6.5 | 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-gsm8k-llama3-3b-base.IQ4_XS.gguf b/sft-gsm8k-llama3-3b-base.IQ4_XS.gguf new file mode 100644 index 0000000..c52ebca --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43cbceb0903f87ded7066e58e24752ca88aea8cdfcc5f8b8e158b7531e7a8a00 +size 1840903520 diff --git a/sft-gsm8k-llama3-3b-base.Q2_K.gguf b/sft-gsm8k-llama3-3b-base.Q2_K.gguf new file mode 100644 index 0000000..e6eedf1 --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386bfe21e306040cf46de511ac88a5d84275c36af149834b39213ba9ab6cf7d6 +size 1363932512 diff --git a/sft-gsm8k-llama3-3b-base.Q3_K_L.gguf b/sft-gsm8k-llama3-3b-base.Q3_K_L.gguf new file mode 100644 index 0000000..91e7797 --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a328bba1d2e736fbc1d178ebe0c875b7ca53e402ebfdad510a2d1b723df3c3ca +size 1815344480 diff --git a/sft-gsm8k-llama3-3b-base.Q3_K_M.gguf b/sft-gsm8k-llama3-3b-base.Q3_K_M.gguf new file mode 100644 index 0000000..8f7ead0 --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9849bcfbda70498f3a32af600d5b927bf73113ad16469327750f34138e8561b0 +size 1687156064 diff --git a/sft-gsm8k-llama3-3b-base.Q3_K_S.gguf b/sft-gsm8k-llama3-3b-base.Q3_K_S.gguf new file mode 100644 index 0000000..2b5ab88 --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61b0c92f9b30eac2d2576930d6ba833069075906322304082956cb4560112ce +size 1542845792 diff --git a/sft-gsm8k-llama3-3b-base.Q4_K_M.gguf b/sft-gsm8k-llama3-3b-base.Q4_K_M.gguf new file mode 100644 index 0000000..0127331 --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dd2a382d0fe9fc4b2e702db87cf50426c414894bcd1be411b0384f0dce1edff +size 2019374432 diff --git a/sft-gsm8k-llama3-3b-base.Q4_K_S.gguf b/sft-gsm8k-llama3-3b-base.Q4_K_S.gguf new file mode 100644 index 0000000..fb0eb72 --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f404a71d943cf126d953ae72aa8f829cc28438b3cc732cf5f723082dd183153 +size 1928197472 diff --git a/sft-gsm8k-llama3-3b-base.Q5_K_M.gguf b/sft-gsm8k-llama3-3b-base.Q5_K_M.gguf new file mode 100644 index 0000000..d7df65e --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b0351b614a5c456372e18d64dd0b1b452cc755bba5e6ac06150ab7fa9f2f29b +size 2322150752 diff --git a/sft-gsm8k-llama3-3b-base.Q5_K_S.gguf b/sft-gsm8k-llama3-3b-base.Q5_K_S.gguf new file mode 100644 index 0000000..65824a6 --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef0e81e30fd11c8e7fae7990a0113e60bb42b8156e5d998150a0b3fda978c28 +size 2269508960 diff --git a/sft-gsm8k-llama3-3b-base.Q6_K.gguf b/sft-gsm8k-llama3-3b-base.Q6_K.gguf new file mode 100644 index 0000000..863ed86 --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28a33de6cf40881e813499d9864846a854ec93347598966c9647717319b92bd9 +size 2643850592 diff --git a/sft-gsm8k-llama3-3b-base.Q8_0.gguf b/sft-gsm8k-llama3-3b-base.Q8_0.gguf new file mode 100644 index 0000000..56b5672 --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31e58e185bfa06b300faec6d95c798147eb7374ff49d4397ed3b378d280283f2 +size 3421896032 diff --git a/sft-gsm8k-llama3-3b-base.f16.gguf b/sft-gsm8k-llama3-3b-base.f16.gguf new file mode 100644 index 0000000..b407861 --- /dev/null +++ b/sft-gsm8k-llama3-3b-base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96bf89c6fac4e6e5316d01de6ed795443b14b2a2001d417592de13519e57bb77 +size 6433684832