commit 374c6e0caba3b0789dd2e99f86fd06f4c5edd993 Author: ModelHub XC Date: Sat Jun 13 14:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Pure-RP-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..30b0d71 --- /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-Pure-RP.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Pure-RP.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Pure-RP.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Pure-RP.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Pure-RP.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Pure-RP.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Pure-RP.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Pure-RP.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Pure-RP.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Pure-RP.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Pure-RP.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Pure-RP.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Pure-RP.IQ4_XS.gguf b/Llama-3.2-3B-Pure-RP.IQ4_XS.gguf new file mode 100644 index 0000000..e5c6fd6 --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78cdba0d5afb2db762a5be039746a75bd686c5f0a4d55ff5da0ee95b34c34be4 +size 1840907392 diff --git a/Llama-3.2-3B-Pure-RP.Q2_K.gguf b/Llama-3.2-3B-Pure-RP.Q2_K.gguf new file mode 100644 index 0000000..6165a4d --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3ce381593f3f3dddf5ee13a77aefd8e6c1051e6822413e996d7949da8f97c50 +size 1363936384 diff --git a/Llama-3.2-3B-Pure-RP.Q3_K_L.gguf b/Llama-3.2-3B-Pure-RP.Q3_K_L.gguf new file mode 100644 index 0000000..55774df --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c10a02af4b0ff545e01f1d1b906296ffa678a674181f16c31371bea7ccfd87eb +size 1815348352 diff --git a/Llama-3.2-3B-Pure-RP.Q3_K_M.gguf b/Llama-3.2-3B-Pure-RP.Q3_K_M.gguf new file mode 100644 index 0000000..a2394d7 --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74124b7728de5d950292c9c9c4dcb3326c45cf2f8c1405c689b114ab4c95e26e +size 1687159936 diff --git a/Llama-3.2-3B-Pure-RP.Q3_K_S.gguf b/Llama-3.2-3B-Pure-RP.Q3_K_S.gguf new file mode 100644 index 0000000..ffa5e70 --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e17ab6915d567677771a0877f13af2a4d5610c64ff6aaababe82e14a65cf22e +size 1542849664 diff --git a/Llama-3.2-3B-Pure-RP.Q4_K_M.gguf b/Llama-3.2-3B-Pure-RP.Q4_K_M.gguf new file mode 100644 index 0000000..2ac5477 --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d457de79b22a4a3f921bb90c43a44181bf2ca3fbb5fcb51e03098bb8e91983 +size 2019378304 diff --git a/Llama-3.2-3B-Pure-RP.Q4_K_S.gguf b/Llama-3.2-3B-Pure-RP.Q4_K_S.gguf new file mode 100644 index 0000000..7c43d3c --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52cbbda1c8b1f5f03679d4abf627960ddb1a7ed89b67787c8bf651d4ddf5ec8d +size 1928201344 diff --git a/Llama-3.2-3B-Pure-RP.Q5_K_M.gguf b/Llama-3.2-3B-Pure-RP.Q5_K_M.gguf new file mode 100644 index 0000000..78bec40 --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c3f2b751dd6da7599c6ec0fe51f4cd6ad3a75c3f0402a492c6c1b0381969782 +size 2322154624 diff --git a/Llama-3.2-3B-Pure-RP.Q5_K_S.gguf b/Llama-3.2-3B-Pure-RP.Q5_K_S.gguf new file mode 100644 index 0000000..dac830e --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb041b88c318b4f149b9acff95f301e3327d7e3147a64a24223f491762a41aa9 +size 2269512832 diff --git a/Llama-3.2-3B-Pure-RP.Q6_K.gguf b/Llama-3.2-3B-Pure-RP.Q6_K.gguf new file mode 100644 index 0000000..34b0b86 --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5a157a62aa28014641ddf4660c1d60d31d555c45585d99d707e36ac8611216b +size 2643854464 diff --git a/Llama-3.2-3B-Pure-RP.Q8_0.gguf b/Llama-3.2-3B-Pure-RP.Q8_0.gguf new file mode 100644 index 0000000..a3f7893 --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9387ac71b9f146e47acebf13689a566da0291c8ff754ac938d2252f4b6e8ec75 +size 3421899904 diff --git a/Llama-3.2-3B-Pure-RP.f16.gguf b/Llama-3.2-3B-Pure-RP.f16.gguf new file mode 100644 index 0000000..7f717f9 --- /dev/null +++ b/Llama-3.2-3B-Pure-RP.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:150d56c29aa155041df304e772da3d9f9d0bec509f062aeef076b058e7b2e9dd +size 6433688704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e0124ce --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/Llama-3.2-3B-Pure-RP +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.2-3B-Pure-RP + + +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-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Pure-RP-GGUF/resolve/main/Llama-3.2-3B-Pure-RP.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. + +