commit 1ddafbda9b73c278d7f2d563e1e00dc6d90bcce5 Author: ModelHub XC Date: Wed Sep 9 10:11:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B_sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d000ba9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-3.2-1B_sft.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B_sft.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B_sft.IQ4_XS.gguf b/Llama-3.2-1B_sft.IQ4_XS.gguf new file mode 100644 index 0000000..298bfb5 --- /dev/null +++ b/Llama-3.2-1B_sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1581cfecfde47392ccb88d246137db5f8267dac8e10c68094275dc4d1fdf0866 +size 748384416 diff --git a/Llama-3.2-1B_sft.Q2_K.gguf b/Llama-3.2-1B_sft.Q2_K.gguf new file mode 100644 index 0000000..825c27c --- /dev/null +++ b/Llama-3.2-1B_sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0418c87ba68b024f51e48ce36ee7b1ab6922bb04e0f1164c6a614b9949d5471b +size 580874400 diff --git a/Llama-3.2-1B_sft.Q3_K_L.gguf b/Llama-3.2-1B_sft.Q3_K_L.gguf new file mode 100644 index 0000000..339c376 --- /dev/null +++ b/Llama-3.2-1B_sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:137b13950322680dd7623402c076f2887b494d568c0ca02ba4d2316747d1e73f +size 732524704 diff --git a/Llama-3.2-1B_sft.Q3_K_M.gguf b/Llama-3.2-1B_sft.Q3_K_M.gguf new file mode 100644 index 0000000..9d526b4 --- /dev/null +++ b/Llama-3.2-1B_sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d2d321ab73aed3ccfd33c9446e92fd6a15eab84e47264e181756d832f507caa +size 690843808 diff --git a/Llama-3.2-1B_sft.Q3_K_S.gguf b/Llama-3.2-1B_sft.Q3_K_S.gguf new file mode 100644 index 0000000..cb8127e --- /dev/null +++ b/Llama-3.2-1B_sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b0697e7186b0adafb5760a1c8489864ed990163310c6f757648af98df6f4c4 +size 641691808 diff --git a/Llama-3.2-1B_sft.Q4_0_4_4.gguf b/Llama-3.2-1B_sft.Q4_0_4_4.gguf new file mode 100644 index 0000000..df1ed87 --- /dev/null +++ b/Llama-3.2-1B_sft.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0db4cb69a0d9154e1b8e7b39d30ac7939764f8dbe5ed5bec4dc79d33adf1b662 +size 770928800 diff --git a/Llama-3.2-1B_sft.Q4_K_M.gguf b/Llama-3.2-1B_sft.Q4_K_M.gguf new file mode 100644 index 0000000..5ffdace --- /dev/null +++ b/Llama-3.2-1B_sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9914f069650069309440c41df476ba4833486c5469da946bac68dbcf1a0cbee4 +size 807694496 diff --git a/Llama-3.2-1B_sft.Q4_K_S.gguf b/Llama-3.2-1B_sft.Q4_K_S.gguf new file mode 100644 index 0000000..f438e55 --- /dev/null +++ b/Llama-3.2-1B_sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76851a08830a540b657eb6b97f33ce46c22ab3df48c8d4dd400ee6ccb5b7b23b +size 775647392 diff --git a/Llama-3.2-1B_sft.Q5_K_M.gguf b/Llama-3.2-1B_sft.Q5_K_M.gguf new file mode 100644 index 0000000..cc5f5ad --- /dev/null +++ b/Llama-3.2-1B_sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe90d2fcc090fb0bf69f9dffdabdde8065d56b4349d9c037ea03be6a60c00928 +size 911503520 diff --git a/Llama-3.2-1B_sft.Q5_K_S.gguf b/Llama-3.2-1B_sft.Q5_K_S.gguf new file mode 100644 index 0000000..c8767ee --- /dev/null +++ b/Llama-3.2-1B_sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f936ef4efc25831889518296c25dfdfee331b46f53f9d20fe5c420d95f46b27 +size 892563616 diff --git a/Llama-3.2-1B_sft.Q6_K.gguf b/Llama-3.2-1B_sft.Q6_K.gguf new file mode 100644 index 0000000..51bb864 --- /dev/null +++ b/Llama-3.2-1B_sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:771684a152bf7f35731a52138d6969c5bf8e52ba75e310a0ef1e037e1faf0a13 +size 1021800608 diff --git a/Llama-3.2-1B_sft.Q8_0.gguf b/Llama-3.2-1B_sft.Q8_0.gguf new file mode 100644 index 0000000..4b4b468 --- /dev/null +++ b/Llama-3.2-1B_sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e6dfc7c08793204d37e5e1c718527c770bb6182f248fbc6f294e5da52553de1 +size 1321083040 diff --git a/Llama-3.2-1B_sft.f16.gguf b/Llama-3.2-1B_sft.f16.gguf new file mode 100644 index 0000000..c340292 --- /dev/null +++ b/Llama-3.2-1B_sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:860f7b448c953d9c2a2115008206154ecd516ca3a8bc7682d433ffd952e07188 +size 2479595680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7d5da1c --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: KSU-HW-SEC/Llama-3.2-1B_sft +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/KSU-HW-SEC/Llama-3.2-1B_sft + + +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-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B_sft-GGUF/resolve/main/Llama-3.2-1B_sft.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. + +