commit cc32208c8514fe8c7b22ef8984470e356fdf7fba Author: ModelHub XC Date: Tue Jun 30 13:45:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4fae7fd --- /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_SmartiPantz_0.21_bf16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_SmartiPantz_0.21_bf16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_SmartiPantz_0.21_bf16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_SmartiPantz_0.21_bf16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_SmartiPantz_0.21_bf16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_SmartiPantz_0.21_bf16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_SmartiPantz_0.21_bf16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_SmartiPantz_0.21_bf16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_SmartiPantz_0.21_bf16.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.IQ4_XS.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.IQ4_XS.gguf new file mode 100644 index 0000000..4066363 --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a74deaa827a42997686e9332d4b24942b0059bf8eea7a444642910257749a72 +size 1840908192 diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q2_K.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q2_K.gguf new file mode 100644 index 0000000..2d0183c --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6600a07f6a6eeefc07e5c6cfacdc49699d003a14bd69a8519a3b65157e846814 +size 1363937184 diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_L.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_L.gguf new file mode 100644 index 0000000..26b91a7 --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce22c19a6c575c72e8358c7d23cff0a2d6bb3cbd22e018fddea02aea1783e95e +size 1815349152 diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_M.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_M.gguf new file mode 100644 index 0000000..fe8791e --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de9c8c5c2f5d38b7bc96467647f84889fae7e1813a31bf395c87f2464be5b994 +size 1687160736 diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_S.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_S.gguf new file mode 100644 index 0000000..5fac43f --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab92e18eef6f3549506032dd6c60f6cd05ea85c29e58ee635754f1c5430565e5 +size 1542850464 diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q4_K_M.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q4_K_M.gguf new file mode 100644 index 0000000..8b5a35a --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:472282b243c159544ffe8ab23e362fb3e248d6dccef0e9df4c09d24951fdebb4 +size 2019379104 diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q4_K_S.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q4_K_S.gguf new file mode 100644 index 0000000..ff4bb90 --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c7426d544693f7d66a000fdd468bee3162d9605889c86ff74b41c0bf413726 +size 1928202144 diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q5_K_M.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q5_K_M.gguf new file mode 100644 index 0000000..6413e26 --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fb42fe70619ce4ef3da9edb9c471e4cf57491d64384061dcd3c762371d536a4 +size 2322155424 diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q5_K_S.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q5_K_S.gguf new file mode 100644 index 0000000..aeb8afb --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f58433256caac52637bd878ea8bc282742eb7f73977090648ee2c9a119b91eca +size 2269513632 diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q6_K.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q6_K.gguf new file mode 100644 index 0000000..def3042 --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c946c90e359908e298a1503886f6725bfc46139c81247919f5d58049228d82 +size 2643855264 diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q8_0.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q8_0.gguf new file mode 100644 index 0000000..856440c --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:affcb3630449188311a85599827b163a87b7a2c5c4356a1099ce535bfa36eac8 +size 3421900704 diff --git a/Llama_3.2_3b_SmartiPantz_0.21_bf16.f16.gguf b/Llama_3.2_3b_SmartiPantz_0.21_bf16.f16.gguf new file mode 100644 index 0000000..3e629d7 --- /dev/null +++ b/Llama_3.2_3b_SmartiPantz_0.21_bf16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed66aae62acd35f8ff85adc95c996d06f937c955f4d4f6ffe6d86940add09394 +size 6433689504 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dbd4167 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Nexesenex/Llama_3.2_3b_SmartiPantz_0.21 +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/Llama_3.2_3b_SmartiPantz_0.21 + + +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_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_SmartiPantz_0.21_bf16-GGUF/resolve/main/Llama_3.2_3b_SmartiPantz_0.21_bf16.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. + +