commit 7845371ca32fd36f6c0301fe6771d8b39a3eb43d Author: ModelHub XC Date: Fri Oct 16 06:29:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/sft-prm800k-llama31-8b-steptok-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..faa6a88 --- /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-prm800k-llama31-8b-steptok.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sft-prm800k-llama31-8b-steptok.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +sft-prm800k-llama31-8b-steptok.f16.gguf filter=lfs diff=lfs merge=lfs -text +sft-prm800k-llama31-8b-steptok.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sft-prm800k-llama31-8b-steptok.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +sft-prm800k-llama31-8b-steptok.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-prm800k-llama31-8b-steptok.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sft-prm800k-llama31-8b-steptok.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +sft-prm800k-llama31-8b-steptok.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-prm800k-llama31-8b-steptok.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sft-prm800k-llama31-8b-steptok.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sft-prm800k-llama31-8b-steptok.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..dcdf981 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Asap7772/sft-prm800k-llama31-8b-steptok +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Asap7772/sft-prm800k-llama31-8b-steptok + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#sft-prm800k-llama31-8b-steptok-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-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/sft-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/sft-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/sft-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/sft-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/sft-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sft-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sft-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/sft-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/sft-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/sft-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/sft-prm800k-llama31-8b-steptok-GGUF/resolve/main/sft-prm800k-llama31-8b-steptok.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-prm800k-llama31-8b-steptok.IQ4_XS.gguf b/sft-prm800k-llama31-8b-steptok.IQ4_XS.gguf new file mode 100644 index 0000000..0379f13 --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d114ca70b8f2396e5f3926b675a1e8167b133e5b396d3778dc901323e6d52084 +size 4484395584 diff --git a/sft-prm800k-llama31-8b-steptok.Q2_K.gguf b/sft-prm800k-llama31-8b-steptok.Q2_K.gguf new file mode 100644 index 0000000..9204bd8 --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e4ffbcb3bd85da4f049809ba7a6969766f050787fa5cb76cecfb0fe3be37c83 +size 3179160064 diff --git a/sft-prm800k-llama31-8b-steptok.Q3_K_L.gguf b/sft-prm800k-llama31-8b-steptok.Q3_K_L.gguf new file mode 100644 index 0000000..8cca60f --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2585faa5246efd00bc59c94805e1f44b6072779056f8a7f88b9c05891c9ab684 +size 4321987104 diff --git a/sft-prm800k-llama31-8b-steptok.Q3_K_M.gguf b/sft-prm800k-llama31-8b-steptok.Q3_K_M.gguf new file mode 100644 index 0000000..1503bb3 --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce9c6912ccf2af3be276bf89416ecced2415d2580289b7f9605bfbeadddc621a +size 4018948640 diff --git a/sft-prm800k-llama31-8b-steptok.Q3_K_S.gguf b/sft-prm800k-llama31-8b-steptok.Q3_K_S.gguf new file mode 100644 index 0000000..581b16b --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce3d09f5626ce415fcbd40398dd828ff1433f4a674470a03d1bf610afbe114fa +size 3664529952 diff --git a/sft-prm800k-llama31-8b-steptok.Q4_K_M.gguf b/sft-prm800k-llama31-8b-steptok.Q4_K_M.gguf new file mode 100644 index 0000000..723572e --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41da0e153cef4d1ef79f87cdc53c47450eb918216ed6e1b586a6825d419fa5b5 +size 4920767680 diff --git a/sft-prm800k-llama31-8b-steptok.Q4_K_S.gguf b/sft-prm800k-llama31-8b-steptok.Q4_K_S.gguf new file mode 100644 index 0000000..5e3d01f --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b44464354cae1e5eb19cd398d4ec58467313b42807d4f1f65d23d9fda51a91bf +size 4692702400 diff --git a/sft-prm800k-llama31-8b-steptok.Q5_K_M.gguf b/sft-prm800k-llama31-8b-steptok.Q5_K_M.gguf new file mode 100644 index 0000000..19add52 --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c68fff99ddcf0c9358cae2ba3a2bf9a8163f2198bdc61581080f7dab357cbff +size 5733023424 diff --git a/sft-prm800k-llama31-8b-steptok.Q5_K_S.gguf b/sft-prm800k-llama31-8b-steptok.Q5_K_S.gguf new file mode 100644 index 0000000..37ad0e6 --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8092d8ad92f76cf92aa2080f1947df0c1f0adc43b38cec1627eace67f0b8774 +size 5599329984 diff --git a/sft-prm800k-llama31-8b-steptok.Q6_K.gguf b/sft-prm800k-llama31-8b-steptok.Q6_K.gguf new file mode 100644 index 0000000..2573daa --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba7f537134c25e16c52d05bfe58c705baf15e95354cb27bfd5e6749c0ee5901b +size 6596045152 diff --git a/sft-prm800k-llama31-8b-steptok.Q8_0.gguf b/sft-prm800k-llama31-8b-steptok.Q8_0.gguf new file mode 100644 index 0000000..0668405 --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c290471f068a62841a217e91a107f9c699c27d87199983c12302b22553f4e2 +size 8540819488 diff --git a/sft-prm800k-llama31-8b-steptok.f16.gguf b/sft-prm800k-llama31-8b-steptok.f16.gguf new file mode 100644 index 0000000..40c0e26 --- /dev/null +++ b/sft-prm800k-llama31-8b-steptok.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d537ee7c20301dbdbcf3e7ee93ce588ee8b2c402248a07239675cab02c867c9d +size 16068978208