commit a00b8a65db5f58e2253664d1b992cba441afa98d Author: ModelHub XC Date: Fri May 15 17:36:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llamalicious3.2-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7ac5596 --- /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 +llamalicious3.2-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8b0b0c0 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: marcuscedricridia/llamalicious3.2-1B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/marcuscedricridia/llamalicious3.2-1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llamalicious3.2-1B-GGUF).*** + +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/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-1B-GGUF/resolve/main/llamalicious3.2-1B.f16.gguf) | f16 | 2.6 | 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. + + diff --git a/llamalicious3.2-1B.IQ4_XS.gguf b/llamalicious3.2-1B.IQ4_XS.gguf new file mode 100644 index 0000000..60624ee --- /dev/null +++ b/llamalicious3.2-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a596cac3a71c0e02e902382574c50d09b0801e2f45d3716f97faceecce9808c +size 748385568 diff --git a/llamalicious3.2-1B.Q2_K.gguf b/llamalicious3.2-1B.Q2_K.gguf new file mode 100644 index 0000000..44c2cb7 --- /dev/null +++ b/llamalicious3.2-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c2b4bee1ad93a04217597b2f40757c3f78ecb301c7e7bac9daf38d3931f3c9d +size 580875552 diff --git a/llamalicious3.2-1B.Q3_K_L.gguf b/llamalicious3.2-1B.Q3_K_L.gguf new file mode 100644 index 0000000..42a5dba --- /dev/null +++ b/llamalicious3.2-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab38b0c1cf8eff7c7a3e1e339fd400f5c08e4ad02d175509d62c1d0e1e323bdf +size 732525856 diff --git a/llamalicious3.2-1B.Q3_K_M.gguf b/llamalicious3.2-1B.Q3_K_M.gguf new file mode 100644 index 0000000..03b0745 --- /dev/null +++ b/llamalicious3.2-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734d0ebcef6ec0d9575cb5c49f5fa039619b1bbaff5c128f1367722f89d1cd4e +size 690844960 diff --git a/llamalicious3.2-1B.Q3_K_S.gguf b/llamalicious3.2-1B.Q3_K_S.gguf new file mode 100644 index 0000000..3d7009b --- /dev/null +++ b/llamalicious3.2-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b57a0cdda300d136d324af27bd8869bc2532c5b48c48401be10c5df1e5e76fc +size 641692960 diff --git a/llamalicious3.2-1B.Q4_K_M.gguf b/llamalicious3.2-1B.Q4_K_M.gguf new file mode 100644 index 0000000..d2c4b10 --- /dev/null +++ b/llamalicious3.2-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04da1d172fd3eee66baccd977062b26ed7b6de6514f0936c981aba6d265f6199 +size 807695648 diff --git a/llamalicious3.2-1B.Q4_K_S.gguf b/llamalicious3.2-1B.Q4_K_S.gguf new file mode 100644 index 0000000..a21e740 --- /dev/null +++ b/llamalicious3.2-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2cacef431e751b8d9c0539917466dfbcb5b98692fb2f681ec77220c6afbcae5 +size 775648544 diff --git a/llamalicious3.2-1B.Q5_K_M.gguf b/llamalicious3.2-1B.Q5_K_M.gguf new file mode 100644 index 0000000..cd1fd23 --- /dev/null +++ b/llamalicious3.2-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b0f0939235985515301d8c8163a1f11d35515a2c19dcf88c1d8c3ce70956ad +size 911504672 diff --git a/llamalicious3.2-1B.Q5_K_S.gguf b/llamalicious3.2-1B.Q5_K_S.gguf new file mode 100644 index 0000000..7faa840 --- /dev/null +++ b/llamalicious3.2-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e820d7c43d66774298e900b580bcc57c438ba6cce5b27f0f429d3f79606e0964 +size 892564768 diff --git a/llamalicious3.2-1B.Q6_K.gguf b/llamalicious3.2-1B.Q6_K.gguf new file mode 100644 index 0000000..2cae98c --- /dev/null +++ b/llamalicious3.2-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81b88801537de9e75f98682aa36d8a7e12dfdd26a4aaa19f45c1dd734a4f20ba +size 1021801760 diff --git a/llamalicious3.2-1B.Q8_0.gguf b/llamalicious3.2-1B.Q8_0.gguf new file mode 100644 index 0000000..2d3ad6c --- /dev/null +++ b/llamalicious3.2-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11addeba507efe1267ea911eafcfdfb1b269277b46bf2497d5f37eaf3430592c +size 1321084192 diff --git a/llamalicious3.2-1B.f16.gguf b/llamalicious3.2-1B.f16.gguf new file mode 100644 index 0000000..0ae7109 --- /dev/null +++ b/llamalicious3.2-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96312757181efdfc9580ca63c68e5bf993bcfe598877e73bf08d53fa13cc1be5 +size 2479596832