commit 52657497152c9e3e4817f9d1f354672bce01e260 Author: ModelHub XC Date: Fri Jun 12 06:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llamalicious3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d9bf38d --- /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 +llamalicious3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llamalicious3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d4d0658 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: marcuscedricridia/llamalicious3.2-3B +datasets: +- marcuscedricridia/alpine1.1-multireq-instructions +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/llamalicious3.2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llamalicious3.2-3B-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/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llamalicious3.2-3B-GGUF/resolve/main/llamalicious3.2-3B.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. + + diff --git a/llamalicious3.2-3B.IQ4_XS.gguf b/llamalicious3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..edc2f69 --- /dev/null +++ b/llamalicious3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f766f14667ad263301f673107b005ba8b5c0bab92afed4e7cd584b07f5aea267 +size 1840908288 diff --git a/llamalicious3.2-3B.Q2_K.gguf b/llamalicious3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..d1b34a0 --- /dev/null +++ b/llamalicious3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f87daf197479d67ef943f0bba00a7a8f3bd639e5af9e1eac117723a7d23c9c1 +size 1363937280 diff --git a/llamalicious3.2-3B.Q3_K_L.gguf b/llamalicious3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..523c807 --- /dev/null +++ b/llamalicious3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e3408b15f30ae99975c9283324568f4d1d65c4ec425d9d2837ad02f2b4c4d1d +size 1815349248 diff --git a/llamalicious3.2-3B.Q3_K_M.gguf b/llamalicious3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..3bb20ea --- /dev/null +++ b/llamalicious3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f456554d1992e7924ec98f56a2e6199eb3eccd7eda4927b486ebf417d537e8a2 +size 1687160832 diff --git a/llamalicious3.2-3B.Q3_K_S.gguf b/llamalicious3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..360df37 --- /dev/null +++ b/llamalicious3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:387b5c8cf217ba380fda5e66281e91b7e3fb59e75727f7a9aedf637ee61bdd50 +size 1542850560 diff --git a/llamalicious3.2-3B.Q4_K_M.gguf b/llamalicious3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..146c8b2 --- /dev/null +++ b/llamalicious3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce9b7a1f8f67d64a1fb3e17b219148e260ca9040a2e0ea9a206ff4dcdb255c0 +size 2019379200 diff --git a/llamalicious3.2-3B.Q4_K_S.gguf b/llamalicious3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..f279a08 --- /dev/null +++ b/llamalicious3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ebf27a1a31588318afb87734d69fc54a494db0472584fee170c83cc5b91215e +size 1928202240 diff --git a/llamalicious3.2-3B.Q5_K_M.gguf b/llamalicious3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..ba2ed5e --- /dev/null +++ b/llamalicious3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e061e4efa487714e77581cb0b273447d57b42ab34e7d50cb7ad8c0870e83eb48 +size 2322155520 diff --git a/llamalicious3.2-3B.Q5_K_S.gguf b/llamalicious3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..2a9349e --- /dev/null +++ b/llamalicious3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ac3d890ca0ca51c2cb785c7974c7f636f218385a526445cdac21c18e74de0a +size 2269513728 diff --git a/llamalicious3.2-3B.Q6_K.gguf b/llamalicious3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..5bb4a9e --- /dev/null +++ b/llamalicious3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80530b452517e4170a38bf7e53039796fd3597517079fefed65d580f4aeaa677 +size 2643855360 diff --git a/llamalicious3.2-3B.Q8_0.gguf b/llamalicious3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..3dc1932 --- /dev/null +++ b/llamalicious3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551e2849ec1933f167e11e209d2b70b0d560e117c9bb4801131500967bcb448d +size 3421900800 diff --git a/llamalicious3.2-3B.f16.gguf b/llamalicious3.2-3B.f16.gguf new file mode 100644 index 0000000..bdaaa31 --- /dev/null +++ b/llamalicious3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a50d23bf4c625088133044d7690615d537cdfbd7a4386ba177d501e2ef16d500 +size 6433689600