commit f8edf149538d2c02a04585459ec801ab17a5f8c2 Author: ModelHub XC Date: Fri Jun 12 19:16:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Oat-Zero-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8647c0a --- /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-Oat-Zero.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Oat-Zero.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Oat-Zero.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Oat-Zero.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Oat-Zero.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Oat-Zero.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Oat-Zero.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Oat-Zero.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Oat-Zero.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Oat-Zero.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Oat-Zero.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Oat-Zero.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Oat-Zero.IQ4_XS.gguf b/Llama-3.2-3B-Oat-Zero.IQ4_XS.gguf new file mode 100644 index 0000000..e3abbef --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:032f796ba1405c7d3f3acd0c92d55b2af2f3656bff0b70854d8ad878f80dec78 +size 1840903168 diff --git a/Llama-3.2-3B-Oat-Zero.Q2_K.gguf b/Llama-3.2-3B-Oat-Zero.Q2_K.gguf new file mode 100644 index 0000000..2520639 --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d73629cc573e22473dc62f2091b5ce5eb9bb6cee8953369c7d35addfa3c755b9 +size 1363932160 diff --git a/Llama-3.2-3B-Oat-Zero.Q3_K_L.gguf b/Llama-3.2-3B-Oat-Zero.Q3_K_L.gguf new file mode 100644 index 0000000..6d949dd --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70f3bb0326eceaeef4f91a44e27b03f1fe0d2db6358b61b86157021b1095299e +size 1815344128 diff --git a/Llama-3.2-3B-Oat-Zero.Q3_K_M.gguf b/Llama-3.2-3B-Oat-Zero.Q3_K_M.gguf new file mode 100644 index 0000000..c97f235 --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85478e4f487e9fe2140103600a737ce1652eea852b0d4a5361012a50751a7728 +size 1687155712 diff --git a/Llama-3.2-3B-Oat-Zero.Q3_K_S.gguf b/Llama-3.2-3B-Oat-Zero.Q3_K_S.gguf new file mode 100644 index 0000000..0b0ded4 --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6011e71ba5c3347e75636dd7e72bbc53acec96d4e73fbd6a3348bd0ff6223f4 +size 1542845440 diff --git a/Llama-3.2-3B-Oat-Zero.Q4_K_M.gguf b/Llama-3.2-3B-Oat-Zero.Q4_K_M.gguf new file mode 100644 index 0000000..9a5c41c --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e5ec25725fcee6f2c155726d1d1bba1bcd4f1356a6df1ae678cd289dd040a27 +size 2019374080 diff --git a/Llama-3.2-3B-Oat-Zero.Q4_K_S.gguf b/Llama-3.2-3B-Oat-Zero.Q4_K_S.gguf new file mode 100644 index 0000000..35cf404 --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11124b765492dbef03ecef41a0b74fb3465b2a8aa5bbdd3e435bf345a167e5d0 +size 1928197120 diff --git a/Llama-3.2-3B-Oat-Zero.Q5_K_M.gguf b/Llama-3.2-3B-Oat-Zero.Q5_K_M.gguf new file mode 100644 index 0000000..13d491a --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31df2374645910ec5899b9b487e6827ece68843612170969d6142f5250c36c6e +size 2322150400 diff --git a/Llama-3.2-3B-Oat-Zero.Q5_K_S.gguf b/Llama-3.2-3B-Oat-Zero.Q5_K_S.gguf new file mode 100644 index 0000000..9534721 --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dba30660038345806e1ea3f2e046609c2fccb068d47689e5985ca82950ba0764 +size 2269508608 diff --git a/Llama-3.2-3B-Oat-Zero.Q6_K.gguf b/Llama-3.2-3B-Oat-Zero.Q6_K.gguf new file mode 100644 index 0000000..d671141 --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acbd4e687de0b68ae7bbd24bb8cbf6603ec1970bd94f6ef192f8276c643f96dc +size 2643850240 diff --git a/Llama-3.2-3B-Oat-Zero.Q8_0.gguf b/Llama-3.2-3B-Oat-Zero.Q8_0.gguf new file mode 100644 index 0000000..0462334 --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:648adbd1c36da2e68a4065d2f7e50d6e360d7c146b0875f65e715e3d5c1fda66 +size 3421895680 diff --git a/Llama-3.2-3B-Oat-Zero.f16.gguf b/Llama-3.2-3B-Oat-Zero.f16.gguf new file mode 100644 index 0000000..53a2313 --- /dev/null +++ b/Llama-3.2-3B-Oat-Zero.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8037be9ef981c2fedf410af362d6d369fd95f9566b150e85426ce84bcdab4884 +size 6433684480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0e769ad --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: sail/Llama-3.2-3B-Oat-Zero +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/sail/Llama-3.2-3B-Oat-Zero + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-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-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Oat-Zero-GGUF/resolve/main/Llama-3.2-3B-Oat-Zero.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. + +