commit dd1682475789b9e505b8c80fd2eefb5d6ec44cb4 Author: ModelHub XC Date: Mon Sep 28 13:47:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ffc92d4 --- /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-ProdigyPlus.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ProdigyPlus.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ProdigyPlus.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ProdigyPlus.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ProdigyPlus.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ProdigyPlus.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ProdigyPlus.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ProdigyPlus.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ProdigyPlus.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ProdigyPlus.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ProdigyPlus.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ProdigyPlus.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-ProdigyPlus.IQ4_XS.gguf b/Llama-3.2-3B-ProdigyPlus.IQ4_XS.gguf new file mode 100644 index 0000000..7a0450d --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6a766efed992a0a361a78a7189d7d307ecabc647cc2e8a743aa7057feb3d2b7 +size 2050222176 diff --git a/Llama-3.2-3B-ProdigyPlus.Q2_K.gguf b/Llama-3.2-3B-ProdigyPlus.Q2_K.gguf new file mode 100644 index 0000000..661d025 --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:844de143d6279007fbb41111a6ba7ebf89a1e04852294add933a8771fda19acd +size 1493219424 diff --git a/Llama-3.2-3B-ProdigyPlus.Q3_K_L.gguf b/Llama-3.2-3B-ProdigyPlus.Q3_K_L.gguf new file mode 100644 index 0000000..17d22a7 --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59e2b2ecca5376a049181e8b89ea1e088a2c8d5670daf968464b6361850a5a11 +size 1984647264 diff --git a/Llama-3.2-3B-ProdigyPlus.Q3_K_M.gguf b/Llama-3.2-3B-ProdigyPlus.Q3_K_M.gguf new file mode 100644 index 0000000..9bcf61c --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5fcd9ce75254720b877653d2fd54ae25646ffd76b13d0bd3ff901971780cf11 +size 1856458848 diff --git a/Llama-3.2-3B-ProdigyPlus.Q3_K_S.gguf b/Llama-3.2-3B-ProdigyPlus.Q3_K_S.gguf new file mode 100644 index 0000000..a400e6c --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f45071dcafc08acb36866fc807597610ac5fb2f8cfe62baa9ee537e839751c68 +size 1712148576 diff --git a/Llama-3.2-3B-ProdigyPlus.Q4_K_M.gguf b/Llama-3.2-3B-ProdigyPlus.Q4_K_M.gguf new file mode 100644 index 0000000..b3414bd --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25fc5b6b3f5b5851ab4f72e454cfcf368030edcb58e6715d204d6b65721cb66b +size 2241005664 diff --git a/Llama-3.2-3B-ProdigyPlus.Q4_K_S.gguf b/Llama-3.2-3B-ProdigyPlus.Q4_K_S.gguf new file mode 100644 index 0000000..7e04023 --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9be3fd94f59c814da2c31bf501f26b7db8881fe581017344309681c367eaf5a +size 2149828704 diff --git a/Llama-3.2-3B-ProdigyPlus.Q5_K_M.gguf b/Llama-3.2-3B-ProdigyPlus.Q5_K_M.gguf new file mode 100644 index 0000000..c6590f8 --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0571c76e9ac73fc7bf404e37e16fa1138d9e0ad5ba7ff16863e7c56c4a7412 +size 2593032288 diff --git a/Llama-3.2-3B-ProdigyPlus.Q5_K_S.gguf b/Llama-3.2-3B-ProdigyPlus.Q5_K_S.gguf new file mode 100644 index 0000000..d69d43c --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd56a7fc9014f51d45e75091e5fd46c665184385945567dc4ee7ab3193a9d5b2 +size 2540390496 diff --git a/Llama-3.2-3B-ProdigyPlus.Q6_K.gguf b/Llama-3.2-3B-ProdigyPlus.Q6_K.gguf new file mode 100644 index 0000000..27291bb --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:359f80339ca9a15b2ba1a67966b6f5dd23a0138f81d9ffd518fe6dca2c6f64c8 +size 2967060576 diff --git a/Llama-3.2-3B-ProdigyPlus.Q8_0.gguf b/Llama-3.2-3B-ProdigyPlus.Q8_0.gguf new file mode 100644 index 0000000..79230fb --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc88c05b00524e93d367dd03855449d4aa9164aba3d2af24f1059cd4f5be0296 +size 3840528480 diff --git a/Llama-3.2-3B-ProdigyPlus.f16.gguf b/Llama-3.2-3B-ProdigyPlus.f16.gguf new file mode 100644 index 0000000..dac6cad --- /dev/null +++ b/Llama-3.2-3B-ProdigyPlus.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcd60b78318a1b7353d70b4aebdc9edd6894aedd3bc97ae668ddc02395d2b6aa +size 7221694560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..158089a --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/Llama-3.2-3B-ProdigyPlus +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.2-3B-ProdigyPlus + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-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-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ProdigyPlus-GGUF/resolve/main/Llama-3.2-3B-ProdigyPlus.f16.gguf) | f16 | 7.3 | 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. + +