commit d519e1fb04077a9db60bd1d43b52f53b43bde364 Author: ModelHub XC Date: Sat Sep 19 02:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ce895ef --- /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-ascii-cats-full.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ascii-cats-full.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ascii-cats-full.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ascii-cats-full.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ascii-cats-full.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ascii-cats-full.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ascii-cats-full.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ascii-cats-full.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ascii-cats-full.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ascii-cats-full.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ascii-cats-full.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ascii-cats-full.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-ascii-cats-full.IQ4_XS.gguf b/Llama-3.2-3B-ascii-cats-full.IQ4_XS.gguf new file mode 100644 index 0000000..1cfa94c --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19ed85ddbdc13850ba6f769d2891a38456c5763c47af1ff5c30614f3db7d83f1 +size 1840903456 diff --git a/Llama-3.2-3B-ascii-cats-full.Q2_K.gguf b/Llama-3.2-3B-ascii-cats-full.Q2_K.gguf new file mode 100644 index 0000000..36b30f6 --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad7a971e8a0b1a7dd55e723fb69d81c58430530b4351bc43e0491510e559a41c +size 1363932448 diff --git a/Llama-3.2-3B-ascii-cats-full.Q3_K_L.gguf b/Llama-3.2-3B-ascii-cats-full.Q3_K_L.gguf new file mode 100644 index 0000000..4638347 --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a234aa81a0859668c01c3eba3b8021e3ebb399a61a153796421a2221bf7e4ccc +size 1815344416 diff --git a/Llama-3.2-3B-ascii-cats-full.Q3_K_M.gguf b/Llama-3.2-3B-ascii-cats-full.Q3_K_M.gguf new file mode 100644 index 0000000..0c7e866 --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d4d2f3a7de6cb96d06f1a361f0a505f97e115d1594657f268a4fc319be5c119 +size 1687156000 diff --git a/Llama-3.2-3B-ascii-cats-full.Q3_K_S.gguf b/Llama-3.2-3B-ascii-cats-full.Q3_K_S.gguf new file mode 100644 index 0000000..4292de4 --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d6090f55a353359a8ac15848dac50b79357ba36ddc28770cc2fb390bff0139 +size 1542845728 diff --git a/Llama-3.2-3B-ascii-cats-full.Q4_K_M.gguf b/Llama-3.2-3B-ascii-cats-full.Q4_K_M.gguf new file mode 100644 index 0000000..1cbd609 --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f72e4f4e913d90e8169f0c004a4bd2c8c8cc0b8901ab0338366fc04fc05f238 +size 2019374368 diff --git a/Llama-3.2-3B-ascii-cats-full.Q4_K_S.gguf b/Llama-3.2-3B-ascii-cats-full.Q4_K_S.gguf new file mode 100644 index 0000000..8043b6f --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c57a5a156adbf302a16a5fa1ca64763062ba2306af5204a2d526dc3f455a2fd +size 1928197408 diff --git a/Llama-3.2-3B-ascii-cats-full.Q5_K_M.gguf b/Llama-3.2-3B-ascii-cats-full.Q5_K_M.gguf new file mode 100644 index 0000000..8f2f184 --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dbc6d5528bc64ee1011691b461a48a7cc52f141a850e1ecded6870a6639dac9 +size 2322150688 diff --git a/Llama-3.2-3B-ascii-cats-full.Q5_K_S.gguf b/Llama-3.2-3B-ascii-cats-full.Q5_K_S.gguf new file mode 100644 index 0000000..4178505 --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7b3a527776f042ec431dfb8daa5ff14fce88861da008b37a451c942af235027 +size 2269508896 diff --git a/Llama-3.2-3B-ascii-cats-full.Q6_K.gguf b/Llama-3.2-3B-ascii-cats-full.Q6_K.gguf new file mode 100644 index 0000000..0ebe9a5 --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7f5bae63601c3b1c89b1adbdb648575262286bbb5f5394e65087ad8d2aa875a +size 2643850528 diff --git a/Llama-3.2-3B-ascii-cats-full.Q8_0.gguf b/Llama-3.2-3B-ascii-cats-full.Q8_0.gguf new file mode 100644 index 0000000..00076f9 --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b34caaca26467c251a7f4fd444ef564acbbfd86147c91cfa953e55e7cb53406 +size 3421895968 diff --git a/Llama-3.2-3B-ascii-cats-full.f16.gguf b/Llama-3.2-3B-ascii-cats-full.f16.gguf new file mode 100644 index 0000000..0544c92 --- /dev/null +++ b/Llama-3.2-3B-ascii-cats-full.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c0828b1af1a724dd65bdfd8205a1bc8d4e76d6c8f8abdd1d553236586dfd36b +size 6433684768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..337ad6b --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: asadhugging/Llama-3.2-3B-ascii-cats-full +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/asadhugging/Llama-3.2-3B-ascii-cats-full + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-ascii-cats-full-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/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ascii-cats-full-GGUF/resolve/main/Llama-3.2-3B-ascii-cats-full.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. + +