commit 611c6066d8d17b7efc75ee136abbfd334460189f Author: ModelHub XC Date: Fri May 15 11:32:45 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dbbfb9e --- /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-Rabbit-Ko-1B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Rabbit-Ko-1B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Rabbit-Ko-1B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Rabbit-Ko-1B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Rabbit-Ko-1B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Rabbit-Ko-1B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Rabbit-Ko-1B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Rabbit-Ko-1B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Rabbit-Ko-1B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.IQ4_XS.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..9920d90 --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e8e853f1a2e7ad013f55fcb19ea23a987f51f8f8064b0629d8ec73a998e86d5 +size 748381952 diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.Q2_K.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..5c3d840 --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78f19e93476e37c796f392cb15db60563fba1154c1cc84d50a7f5114a98ce784 +size 580871936 diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_L.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..9e28cdf --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc1943a4f4a2cf8ee2494a15f533d772c92468451f0b33430a6f8c387917b016 +size 732522240 diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_M.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..949534d --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cf97de0cb9d110529b886a291592432f6a6a1ed21015735d90c348136d18bca +size 690841344 diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_S.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..17dcd5e --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd858c23431406b4669499251d74036897aa8d95d63673d646463fe25742a61c +size 641689344 diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.Q4_K_M.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..6a769bd --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3410fc815ffc85819d85eeeedf086caa6fe862bd557c76b3dd9959092320757f +size 807692032 diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.Q4_K_S.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..c14b584 --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be1ca3d340682655df213dce6de572630ee184b546cf5d942dfc032ef21a53d +size 775644928 diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.Q5_K_M.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..8cbae89 --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc21ac8034a117e0884b4132316977bb09d9f4685acb618130802789763d0fcd +size 911501056 diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.Q5_K_S.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..9ccd7de --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0199713985194d0036680382b23fd43e3f167cc0dd6cbcbeef0ce76523cf4eb5 +size 892561152 diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.Q6_K.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..4ea4374 --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e7451e91017db167b4d348631f8ce0aa4883bcc9a017451b294f0adb64d2feb +size 1021798144 diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.Q8_0.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..c4177d8 --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c3e9c8e7c1acc4bee54c4283d24b25a8d356b055312c2624e2b30e2d59895a +size 1321080576 diff --git a/Llama-3.2-Rabbit-Ko-1B-Instruct.f16.gguf b/Llama-3.2-Rabbit-Ko-1B-Instruct.f16.gguf new file mode 100644 index 0000000..4c476f4 --- /dev/null +++ b/Llama-3.2-Rabbit-Ko-1B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6b0acc3fa68865c560acc9976169ddddbcc9266baac9043a81d0e5c2c0210ba +size 2479593216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cd7a2fd --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: CarrotAI/Llama-3.2-Rabbit-Ko-1B-Instruct +datasets: +- CarrotAI/ko-instruction-dataset +- CarrotAI/Magpie-Ko-Pro-AIR +language: +- ko +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/CarrotAI/Llama-3.2-Rabbit-Ko-1B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-i1-GGUF +## 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-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Rabbit-Ko-1B-Instruct-GGUF/resolve/main/Llama-3.2-Rabbit-Ko-1B-Instruct.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. + +