commit b1fa745668a459db04946881702eb517d97f0ae4 Author: ModelHub XC Date: Thu Oct 22 15:07:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..12a585e --- /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-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.IQ4_XS.gguf new file mode 100644 index 0000000..de0120b --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:918dcfe63181b5a2593aebf443f96130f874252cfc8b38893b07cb6219ebd1e4 +size 748384448 diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q2_K.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q2_K.gguf new file mode 100644 index 0000000..d81641f --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfad24c66e720ffc5faebe2a039cbae6ec67c4715522704af8dbefd27847a600 +size 580874432 diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_L.gguf new file mode 100644 index 0000000..993716c --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eeece1cd365f2652503ed8a1c0561d7a637be08773b77554c64930e999804f3 +size 732524736 diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_M.gguf new file mode 100644 index 0000000..236a568 --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155d28612000e77451070ea25c73e7708cca0938b229ecbdee2ddd1a11260f86 +size 690843840 diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_S.gguf new file mode 100644 index 0000000..2a189c7 --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dacf9d69b3ab4ca32e931bdd1409afc2435fe1fed7475af9c0e3d1a0eb9a749c +size 641691840 diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q4_K_M.gguf new file mode 100644 index 0000000..4b8ee71 --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0e2778fbbd7809d53947688de429ea11f79ee91b1a39177c1ba7ee8f1b76a76 +size 807694528 diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q4_K_S.gguf new file mode 100644 index 0000000..aa8c1ed --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c7ee3c28bd59ff4ad5838a26a5adcc19f81ae24d38eddc1bae33a07c4aee7d +size 775647424 diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q5_K_M.gguf new file mode 100644 index 0000000..7927055 --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa160ca176e1b5be3f82d159324c2538b41fd5affd5e588f5bebb2dbe18785f9 +size 911503552 diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q5_K_S.gguf new file mode 100644 index 0000000..4c07468 --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7459fd934b017eba19e3f3172b9bfce07be9616ba706ceb00b79d4a25922f831 +size 892563648 diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q6_K.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q6_K.gguf new file mode 100644 index 0000000..3f4e4b4 --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51ea3a2621af535350f10b461140eaaee0a6eae8975862df98c244d2dbd089fa +size 1021800640 diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q8_0.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q8_0.gguf new file mode 100644 index 0000000..e9cc2cb --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be2bd9ccf43e9113f6019ebd17d55649d1dc78db7933e61375d2824c59a56c4c +size 1321083072 diff --git a/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.f16.gguf b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.f16.gguf new file mode 100644 index 0000000..2ffa187 --- /dev/null +++ b/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4905898c8863d0fbe661a5fe7c838477ef41d06f811528da430f964039abcca1 +size 2479595712 diff --git a/README.md b/README.md new file mode 100644 index 0000000..abf8faa --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: SongTonyLi/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/SongTonyLi/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-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-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6-GGUF/resolve/main/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6.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. + +