commit f676ae1883ed3153041eb95587188c56381bd80f Author: ModelHub XC Date: Sun Jun 28 12:45:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CogBeTh-Llama3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..47fc40e --- /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 +CogBeTh-Llama3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CogBeTh-Llama3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CogBeTh-Llama3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CogBeTh-Llama3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CogBeTh-Llama3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CogBeTh-Llama3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CogBeTh-Llama3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CogBeTh-Llama3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CogBeTh-Llama3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CogBeTh-Llama3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CogBeTh-Llama3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CogBeTh-Llama3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CogBeTh-Llama3.2-3B.IQ4_XS.gguf b/CogBeTh-Llama3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..b1756ad --- /dev/null +++ b/CogBeTh-Llama3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40e009e459458b6232f650048997b1d115f973508623900dd84415d065aafb69 +size 1840908256 diff --git a/CogBeTh-Llama3.2-3B.Q2_K.gguf b/CogBeTh-Llama3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..e789f82 --- /dev/null +++ b/CogBeTh-Llama3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a50b00dab9711d67603358576fe17e700ab629b2d92400145075e673032b2e5 +size 1363937248 diff --git a/CogBeTh-Llama3.2-3B.Q3_K_L.gguf b/CogBeTh-Llama3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..32656af --- /dev/null +++ b/CogBeTh-Llama3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad9bd499eccbf3e3dea09cc771aaec5e5e5c123229b852e190b907c41d81c8d6 +size 1815349216 diff --git a/CogBeTh-Llama3.2-3B.Q3_K_M.gguf b/CogBeTh-Llama3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..2586378 --- /dev/null +++ b/CogBeTh-Llama3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc121dcd50863fb57f0a903e2db3cfdeefa4ba63f5537af4dab380d96bc9c3e8 +size 1687160800 diff --git a/CogBeTh-Llama3.2-3B.Q3_K_S.gguf b/CogBeTh-Llama3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..9090706 --- /dev/null +++ b/CogBeTh-Llama3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60200964c8a7ee9a88c6e742565f48299547b982bdecaca399d0606c5e09b5c3 +size 1542850528 diff --git a/CogBeTh-Llama3.2-3B.Q4_K_M.gguf b/CogBeTh-Llama3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..0da9a89 --- /dev/null +++ b/CogBeTh-Llama3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87c05edc6dc4f875e4afdefe9e0d605dbc34e43b5b0647f40008ac3d4e7b8d99 +size 2019379168 diff --git a/CogBeTh-Llama3.2-3B.Q4_K_S.gguf b/CogBeTh-Llama3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..5378317 --- /dev/null +++ b/CogBeTh-Llama3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0617e1d04449efb76374ce53633593480157892efd45e7f5421d41bedb44a0 +size 1928202208 diff --git a/CogBeTh-Llama3.2-3B.Q5_K_M.gguf b/CogBeTh-Llama3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..4c930ac --- /dev/null +++ b/CogBeTh-Llama3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:290c5305246623cf94e07541bac790d9c81840c084ec1a66cf60e83f147891a4 +size 2322155488 diff --git a/CogBeTh-Llama3.2-3B.Q5_K_S.gguf b/CogBeTh-Llama3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..97c17cd --- /dev/null +++ b/CogBeTh-Llama3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40432693be02e089d9f8fd36c79a1a04f485753bfd0fc245f7a72c921a3b5c33 +size 2269513696 diff --git a/CogBeTh-Llama3.2-3B.Q6_K.gguf b/CogBeTh-Llama3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..ac1c0f5 --- /dev/null +++ b/CogBeTh-Llama3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a69c485b63b9d4d2b2480889dd6f73dd5ca155f813c527019a8fa388fe89948e +size 2643855328 diff --git a/CogBeTh-Llama3.2-3B.Q8_0.gguf b/CogBeTh-Llama3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..06fdf23 --- /dev/null +++ b/CogBeTh-Llama3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1afd8d1641cc192fb079e8418e2716d85216cbd4d6d0c86f3acd39af13b75c04 +size 3421900768 diff --git a/CogBeTh-Llama3.2-3B.f16.gguf b/CogBeTh-Llama3.2-3B.f16.gguf new file mode 100644 index 0000000..252282f --- /dev/null +++ b/CogBeTh-Llama3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92bc38f231228813a4e8c6bd1196c29ea9c0ec7abf84425f142388ce4e7669a4 +size 6433689568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6b143d7 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: theprint/CogBeTh-Llama3.2-3B +datasets: +- theprint/CogBeTh-GPT +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/theprint/CogBeTh-Llama3.2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CogBeTh-Llama3.2-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-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/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CogBeTh-Llama3.2-3B-GGUF/resolve/main/CogBeTh-Llama3.2-3B.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. + +