commit 4b1a2d87207f0a2889b12e2b54293f84ef0365a0 Author: ModelHub XC Date: Sat May 9 18:56:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e6d7d02 --- /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-RRP-V0.4-Sce.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-RRP-V0.4-Sce.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-RRP-V0.4-Sce.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-RRP-V0.4-Sce.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-RRP-V0.4-Sce.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-RRP-V0.4-Sce.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-RRP-V0.4-Sce.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-RRP-V0.4-Sce.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-RRP-V0.4-Sce.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.IQ4_XS.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.IQ4_XS.gguf new file mode 100644 index 0000000..e31d0c8 --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d8eef4770ffbdf167fd9de71b610202c44793c290b91abf8df3a9837b2aedf +size 1840907520 diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.Q2_K.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.Q2_K.gguf new file mode 100644 index 0000000..b0d465d --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95bf678577a6ec85d98d0b066a225b36716a45abe0a47d3d83643ded4d93fefb +size 1363936512 diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_L.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_L.gguf new file mode 100644 index 0000000..7905e3b --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e65376e91bbd4487e50160f4a43b5bd185bc22677b1815a8941dcc85f73966 +size 1815348480 diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_M.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_M.gguf new file mode 100644 index 0000000..7dd764b --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02e11e07350057bb3b428e8ce91e6e82114390bec4a349393179b1fccaaed46 +size 1687160064 diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_S.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_S.gguf new file mode 100644 index 0000000..562955e --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ccb8fd79a58a65cbd9c84cb627b61ae8984c28088f7fac6e77bbd5969d82e65 +size 1542849792 diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.Q4_K_M.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.Q4_K_M.gguf new file mode 100644 index 0000000..2c9e363 --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:606fa0dce03df3b0b198462b40d8123419a43700ba73aa48969f437f9962f422 +size 2019378432 diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.Q4_K_S.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.Q4_K_S.gguf new file mode 100644 index 0000000..ec3f145 --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32ea57a761ac0bb505ddd9dcaedbbdc19ec9933d6a4226cd7879e4b592e6ed97 +size 1928201472 diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.Q5_K_M.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.Q5_K_M.gguf new file mode 100644 index 0000000..bd64884 --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac52efe6139dcd4404af558cb319a463990afc120dfcf0bebdceaf536e158d14 +size 2322154752 diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.Q5_K_S.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.Q5_K_S.gguf new file mode 100644 index 0000000..64bb16c --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f808c21eba2aea52b4d72b723a71bcdfd6605140b84f69fdcbffefe7b50d3398 +size 2269512960 diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.Q6_K.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.Q6_K.gguf new file mode 100644 index 0000000..ace1cfa --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e6a0b4c3e12259d8bf6c45a2174294e1303ae5e1b41af051f87901e674601ea +size 2643854592 diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.Q8_0.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.Q8_0.gguf new file mode 100644 index 0000000..258985b --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d91f0fc2eb621de536c957199f90d457ae1b014e3f4d20eb0a2fb2dce7b7583 +size 3421900032 diff --git a/Llama-3.2-3B-RRP-V0.4-Sce.f16.gguf b/Llama-3.2-3B-RRP-V0.4-Sce.f16.gguf new file mode 100644 index 0000000..a1197fa --- /dev/null +++ b/Llama-3.2-3B-RRP-V0.4-Sce.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4140a4aad48131fdf92f4fdf67a93cf5f8c9d1d5804e73ee78415c8ae1d27e85 +size 6433688832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..416e1a7 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/Llama-3.2-3B-RRP-V0.4-Sce +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.2-3B-RRP-V0.4-Sce + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-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-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-RRP-V0.4-Sce-GGUF/resolve/main/Llama-3.2-3B-RRP-V0.4-Sce.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. + +