commit 02a8fe23f4d1230cf2f4a98174af429d96c8aa2f Author: ModelHub XC Date: Thu Sep 3 13:14:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Loxa-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..97f6db0 --- /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 +Loxa-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Loxa-3B.IQ4_XS.gguf b/Loxa-3B.IQ4_XS.gguf new file mode 100644 index 0000000..2565d4e --- /dev/null +++ b/Loxa-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e063f4dc6d5d9b167fb90f9157a6775af209e2eb1acd80c532992597b2fcbb12 +size 1840907648 diff --git a/Loxa-3B.Q2_K.gguf b/Loxa-3B.Q2_K.gguf new file mode 100644 index 0000000..a0f1878 --- /dev/null +++ b/Loxa-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ed2653fa5af8ce3690d5522816edc16071625dc6762e14dc6765ee537f380d +size 1363936640 diff --git a/Loxa-3B.Q3_K_L.gguf b/Loxa-3B.Q3_K_L.gguf new file mode 100644 index 0000000..cdc4f3a --- /dev/null +++ b/Loxa-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2198e05005a27e4b6ea9e5f789b894efe1f79e0605a77c6e13538f528a311682 +size 1815348608 diff --git a/Loxa-3B.Q3_K_M.gguf b/Loxa-3B.Q3_K_M.gguf new file mode 100644 index 0000000..59fe78f --- /dev/null +++ b/Loxa-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d159d0087844d020c2a36349d30b088da06cb6c2ce460cb518679148896fc008 +size 1687160192 diff --git a/Loxa-3B.Q3_K_S.gguf b/Loxa-3B.Q3_K_S.gguf new file mode 100644 index 0000000..c7675af --- /dev/null +++ b/Loxa-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a60dab41a325cc63a38823a8758ca0098d5dbf6b7e94e0b1cbe278b0836732a7 +size 1542849920 diff --git a/Loxa-3B.Q4_K_M.gguf b/Loxa-3B.Q4_K_M.gguf new file mode 100644 index 0000000..d575bda --- /dev/null +++ b/Loxa-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:177a6055060500b825d27151ce4334cd86209b60eb74e143917d89354a613fae +size 2019378560 diff --git a/Loxa-3B.Q4_K_S.gguf b/Loxa-3B.Q4_K_S.gguf new file mode 100644 index 0000000..e6bce28 --- /dev/null +++ b/Loxa-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37f8207ad46bfbdd422b0f995ff338bd136c65f955973fe65a75093925b7a835 +size 1928201600 diff --git a/Loxa-3B.Q5_K_M.gguf b/Loxa-3B.Q5_K_M.gguf new file mode 100644 index 0000000..ded4f1a --- /dev/null +++ b/Loxa-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f4c41e3f833480f70df82b44945caec0669b0a999201ccb00cb6e399c409fc8 +size 2322154880 diff --git a/Loxa-3B.Q5_K_S.gguf b/Loxa-3B.Q5_K_S.gguf new file mode 100644 index 0000000..c59ebd6 --- /dev/null +++ b/Loxa-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a939a71ff973ba1e7f0f810fd0e6222ce7df81fe3cb6f63dae996d802d70df2 +size 2269513088 diff --git a/Loxa-3B.Q6_K.gguf b/Loxa-3B.Q6_K.gguf new file mode 100644 index 0000000..b219b90 --- /dev/null +++ b/Loxa-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5464cf297bc4e5a2e4fb4a30c8707091ebaac21b7baae67feea69f9fb91dcaf9 +size 2643854720 diff --git a/Loxa-3B.Q8_0.gguf b/Loxa-3B.Q8_0.gguf new file mode 100644 index 0000000..5ef1555 --- /dev/null +++ b/Loxa-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f37d5275486f8a4b9be581e34139f05cd2cf66bd3d4c8684eefe2e17f85bd5d9 +size 3421900160 diff --git a/Loxa-3B.f16.gguf b/Loxa-3B.f16.gguf new file mode 100644 index 0000000..0efaa07 --- /dev/null +++ b/Loxa-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6314adac349ef241844f365f668a72064336c956755d2d00bd094ab84a4113bb +size 6433688960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6a70cba --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: frameai/Loxa-3B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation +- conversational +- language-model +- cpu +--- +## About + + + + + + +static quants of https://huggingface.co/frameai/Loxa-3B + + +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/Loxa-3B-GGUF/resolve/main/Loxa-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-3B-GGUF/resolve/main/Loxa-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-3B-GGUF/resolve/main/Loxa-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Loxa-3B-GGUF/resolve/main/Loxa-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-3B-GGUF/resolve/main/Loxa-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-3B-GGUF/resolve/main/Loxa-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Loxa-3B-GGUF/resolve/main/Loxa-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Loxa-3B-GGUF/resolve/main/Loxa-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-3B-GGUF/resolve/main/Loxa-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-3B-GGUF/resolve/main/Loxa-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Loxa-3B-GGUF/resolve/main/Loxa-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Loxa-3B-GGUF/resolve/main/Loxa-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. + +