commit 716aee639a6dbc80226add393bd6a1ca66eb64ae Author: ModelHub XC Date: Mon Sep 7 19:54:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6fe891f --- /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 +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.IQ4_XS.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.IQ4_XS.gguf new file mode 100644 index 0000000..0602616 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ea050ca37be91373e2d890c7d69ef27c535acbf08e2c1b2cf0960707c340abd +size 1840906880 diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q2_K.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q2_K.gguf new file mode 100644 index 0000000..cad477c --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49cde188b4378e2fd70e5b95f9ffa9db3670d7c37f9719b497431dca2d61edff +size 1363935872 diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_L.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_L.gguf new file mode 100644 index 0000000..17f8d9d --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:181435e8f2f64bab759e9211c7582d20d046a52efb646951780f80f1564fe7ed +size 1815347840 diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_M.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_M.gguf new file mode 100644 index 0000000..1cfcd08 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c422660c4083fe9e68552a5881ad8b8b1266cfa73191433169561c2ab0aae0f +size 1687159424 diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_S.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_S.gguf new file mode 100644 index 0000000..fa5ebc7 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efa99268e95c4fee2df056f6b81b18e671ed0bf3e2ccec010a79774f41421f59 +size 1542849152 diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q4_K_M.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q4_K_M.gguf new file mode 100644 index 0000000..8cb5566 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:613e4869f85885123e36a2e9ce3b646108e9bc50604a622ce94ba6fd9128e875 +size 2019377792 diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q4_K_S.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q4_K_S.gguf new file mode 100644 index 0000000..2e332e6 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60666b43e0c222af85b76c343219a07da1b688b4c912d415b80e89299dec0216 +size 1928200832 diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q5_K_M.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q5_K_M.gguf new file mode 100644 index 0000000..973dd8c --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb23f57f51b2a79679d4b52cddde72fd139b4b933567fd8ddecd3124f31a4a0 +size 2322154112 diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q5_K_S.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q5_K_S.gguf new file mode 100644 index 0000000..d47b5ef --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d47707c7844b353c7d3dc645049f44fb0bab2e2d7587c4667182c5eca4fe9fc +size 2269512320 diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q6_K.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q6_K.gguf new file mode 100644 index 0000000..f559d72 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f728287b43ed957c009088b2cddbdbd67c60c98d1c36d801448c5b35736f9e3c +size 2643853952 diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q8_0.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q8_0.gguf new file mode 100644 index 0000000..fa5a02d --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3efa482dad9184996364df136a332ad7c2c9114d3ff8a2f885bdb51d8709afb +size 3421899392 diff --git a/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.f16.gguf b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.f16.gguf new file mode 100644 index 0000000..95bffb5 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3d14bd1a081d792c5d1228b22f8f2e3b0d83a10a0cc5589fb9b1c0ec2e5e31d +size 6433688192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f79561e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: SongTonyLi/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/SongTonyLi/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-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/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2-GGUF/resolve/main/Llama-3.2-3B-Instruct-SFT-D_chosen-pref-mix2.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. + +