commit d2bd4f4726e57e3dc7d1bd57ad41b320937b68d7 Author: ModelHub XC Date: Sat May 16 02:15:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3b-Based-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..638c724 --- /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-Based.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3b-Based.IQ4_XS.gguf b/Llama-3.2-3b-Based.IQ4_XS.gguf new file mode 100644 index 0000000..fc6461d --- /dev/null +++ b/Llama-3.2-3b-Based.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39932a0359490c3d399028648a13220673f67d756041bb7cb8df5e1a63d6fa0d +size 1840907648 diff --git a/Llama-3.2-3b-Based.Q2_K.gguf b/Llama-3.2-3b-Based.Q2_K.gguf new file mode 100644 index 0000000..ede5be7 --- /dev/null +++ b/Llama-3.2-3b-Based.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:506c829201174910dea56f95e97b3373f4074cd82008b5421af024025c99f5af +size 1363936640 diff --git a/Llama-3.2-3b-Based.Q3_K_L.gguf b/Llama-3.2-3b-Based.Q3_K_L.gguf new file mode 100644 index 0000000..0b0f09f --- /dev/null +++ b/Llama-3.2-3b-Based.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:401324906121622149addb535108a46258048fe687dac36f8747177d55e5526e +size 1815348608 diff --git a/Llama-3.2-3b-Based.Q3_K_M.gguf b/Llama-3.2-3b-Based.Q3_K_M.gguf new file mode 100644 index 0000000..f211a89 --- /dev/null +++ b/Llama-3.2-3b-Based.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea3d09cff9235f3e310e1811292e5f396403b3ae472dce1ef68cd214193fc1d5 +size 1687160192 diff --git a/Llama-3.2-3b-Based.Q3_K_S.gguf b/Llama-3.2-3b-Based.Q3_K_S.gguf new file mode 100644 index 0000000..cbfa772 --- /dev/null +++ b/Llama-3.2-3b-Based.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f6ce5086abf12d97c81ffba2425eef705a706346d0ed5c542246a9764a21524 +size 1542849920 diff --git a/Llama-3.2-3b-Based.Q4_K_M.gguf b/Llama-3.2-3b-Based.Q4_K_M.gguf new file mode 100644 index 0000000..1848b79 --- /dev/null +++ b/Llama-3.2-3b-Based.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8283a8ca0aed9e0225d08d7d356a0779e0cb5c3deeae179a3bb9eee2f3e442b +size 2019378560 diff --git a/Llama-3.2-3b-Based.Q4_K_S.gguf b/Llama-3.2-3b-Based.Q4_K_S.gguf new file mode 100644 index 0000000..8e93326 --- /dev/null +++ b/Llama-3.2-3b-Based.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba9b3e1d6d402c5b67f40a9f852f792300e32144358892c5474588f7b6b4e17a +size 1928201600 diff --git a/Llama-3.2-3b-Based.Q5_K_M.gguf b/Llama-3.2-3b-Based.Q5_K_M.gguf new file mode 100644 index 0000000..a0b5a5f --- /dev/null +++ b/Llama-3.2-3b-Based.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ad29e8fa31ac835e6d8b6bccfc73c48e452faadf9705eb8356a18949a210e21 +size 2322154880 diff --git a/Llama-3.2-3b-Based.Q5_K_S.gguf b/Llama-3.2-3b-Based.Q5_K_S.gguf new file mode 100644 index 0000000..5fe3e38 --- /dev/null +++ b/Llama-3.2-3b-Based.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6940f47bed414be435052466b9d6ba2a6f5de82662ae69f2a76cbc5a2745817 +size 2269513088 diff --git a/Llama-3.2-3b-Based.Q6_K.gguf b/Llama-3.2-3b-Based.Q6_K.gguf new file mode 100644 index 0000000..84e34f3 --- /dev/null +++ b/Llama-3.2-3b-Based.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bcdb9f257a020e473cd206ef42640c18b27b14b3eb0da414508dbefa235a517 +size 2643854720 diff --git a/Llama-3.2-3b-Based.Q8_0.gguf b/Llama-3.2-3b-Based.Q8_0.gguf new file mode 100644 index 0000000..dacc0a6 --- /dev/null +++ b/Llama-3.2-3b-Based.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68926da4672037235437d147d09782d7cac1f02d049526ecd97197a2c3b53e9f +size 3421900160 diff --git a/Llama-3.2-3b-Based.f16.gguf b/Llama-3.2-3b-Based.f16.gguf new file mode 100644 index 0000000..430dfc7 --- /dev/null +++ b/Llama-3.2-3b-Based.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e5460b417d3759f223ccfff14ec48d53d8ddce44369baf1ea88b5b65929d3ae +size 6433688960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..816b139 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: llm4thewin/Llama-3.2-3b-Based +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/llm4thewin/Llama-3.2-3b-Based + + +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-Based-GGUF/resolve/main/Llama-3.2-3b-Based.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-GGUF/resolve/main/Llama-3.2-3b-Based.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-GGUF/resolve/main/Llama-3.2-3b-Based.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-GGUF/resolve/main/Llama-3.2-3b-Based.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-GGUF/resolve/main/Llama-3.2-3b-Based.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-GGUF/resolve/main/Llama-3.2-3b-Based.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-GGUF/resolve/main/Llama-3.2-3b-Based.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-GGUF/resolve/main/Llama-3.2-3b-Based.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-GGUF/resolve/main/Llama-3.2-3b-Based.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-GGUF/resolve/main/Llama-3.2-3b-Based.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-GGUF/resolve/main/Llama-3.2-3b-Based.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-GGUF/resolve/main/Llama-3.2-3b-Based.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. + +