commit ba01a7e9cfe2a35b810a496cf0d037daf92986ed Author: ModelHub XC Date: Fri Sep 11 02:48:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/lexitronLlama3.2-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bdf2318 --- /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 +lexitronLlama3.2-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +lexitronLlama3.2-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +lexitronLlama3.2-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +lexitronLlama3.2-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +lexitronLlama3.2-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lexitronLlama3.2-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +lexitronLlama3.2-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lexitronLlama3.2-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +lexitronLlama3.2-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lexitronLlama3.2-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +lexitronLlama3.2-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +lexitronLlama3.2-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..766dc28 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: jonelganalon/lexitronLlama3.2-3B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/jonelganalon/lexitronLlama3.2-3B-Instruct + + +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/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/lexitronLlama3.2-3B-Instruct-GGUF/resolve/main/lexitronLlama3.2-3B-Instruct.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/lexitronLlama3.2-3B-Instruct.IQ4_XS.gguf b/lexitronLlama3.2-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..07689f8 --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f2cdfcad3800c093ab96b4573c3fcaf68ab16a2d2073c6e8c8afebd2f3af90 +size 1840904384 diff --git a/lexitronLlama3.2-3B-Instruct.Q2_K.gguf b/lexitronLlama3.2-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..18fe512 --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e81ac461effbede4eb33115e77ad63af6cee9dfdaf7a3473cf4e69768ce02bf +size 1363933376 diff --git a/lexitronLlama3.2-3B-Instruct.Q3_K_L.gguf b/lexitronLlama3.2-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..5fd9407 --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:183eb23bc823463edeb5dbb1298ae512385678a843d8f75a43b91d261d22c885 +size 1815345344 diff --git a/lexitronLlama3.2-3B-Instruct.Q3_K_M.gguf b/lexitronLlama3.2-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..cc12cf1 --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af3990cb46a802daf54f4f6419a76f51dd97aead0ef74ce9bcbb26205f7869d +size 1687156928 diff --git a/lexitronLlama3.2-3B-Instruct.Q3_K_S.gguf b/lexitronLlama3.2-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..c4d7ff6 --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7101400f3d5b18a9566d45336dadc7b1a31fd4efc05c58c0f73df4d08b7d52d5 +size 1542846656 diff --git a/lexitronLlama3.2-3B-Instruct.Q4_K_M.gguf b/lexitronLlama3.2-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..ef863e3 --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f46fe432711fb61f77668fcfbda13a10030e859046bbb119e2816c8081c3460 +size 2019375296 diff --git a/lexitronLlama3.2-3B-Instruct.Q4_K_S.gguf b/lexitronLlama3.2-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..49c1bc2 --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfd8972e55e73b46bb09e6f5ef2eb0349f9337e211a8e9cd2770972e18ea9b0f +size 1928198336 diff --git a/lexitronLlama3.2-3B-Instruct.Q5_K_M.gguf b/lexitronLlama3.2-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..a0bb18c --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a352ee908d5c69669f2609a64fe4d36ba75efc004bdc451d00384bca74a6f458 +size 2322151616 diff --git a/lexitronLlama3.2-3B-Instruct.Q5_K_S.gguf b/lexitronLlama3.2-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..66b175a --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f9c038d304797bb9abcf1396aadf22cc9972b0982fb1ecfc1be767dc6e69564 +size 2269509824 diff --git a/lexitronLlama3.2-3B-Instruct.Q6_K.gguf b/lexitronLlama3.2-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..5cdb004 --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09db8abc3ef02fab4e373edf0728d1dd6718b7179eab5e04ae92f1ce9f25e25b +size 2643851456 diff --git a/lexitronLlama3.2-3B-Instruct.Q8_0.gguf b/lexitronLlama3.2-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..00afcfe --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef85c32559557618ccc7af760f084a334896f82bbd2c31058da4d35bb4cea09b +size 3421896896 diff --git a/lexitronLlama3.2-3B-Instruct.f16.gguf b/lexitronLlama3.2-3B-Instruct.f16.gguf new file mode 100644 index 0000000..be18e25 --- /dev/null +++ b/lexitronLlama3.2-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6176140bcd89c715f81a511e7abc595de435677d5dc5b93f290d3629ff700b +size 6433685696