commit eded0adb89cbe3e5e8fd222647eb2579fcf9e6ea Author: ModelHub XC Date: Sat Jul 11 04:01:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLilmonix3b-v0.4a-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3c40737 --- /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 +LLilmonix3b-v0.4a.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLilmonix3b-v0.4a.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLilmonix3b-v0.4a.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLilmonix3b-v0.4a.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLilmonix3b-v0.4a.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLilmonix3b-v0.4a.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLilmonix3b-v0.4a.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLilmonix3b-v0.4a.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLilmonix3b-v0.4a.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLilmonix3b-v0.4a.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLilmonix3b-v0.4a.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLilmonix3b-v0.4a.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLilmonix3b-v0.4a.IQ4_XS.gguf b/LLilmonix3b-v0.4a.IQ4_XS.gguf new file mode 100644 index 0000000..b32c7a9 --- /dev/null +++ b/LLilmonix3b-v0.4a.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:776c13987e553c18b08e55d32aee6e0f7ce8eab847e1af2782ddb0ec692f58ec +size 1995476992 diff --git a/LLilmonix3b-v0.4a.Q2_K.gguf b/LLilmonix3b-v0.4a.Q2_K.gguf new file mode 100644 index 0000000..09f00b0 --- /dev/null +++ b/LLilmonix3b-v0.4a.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f43d7d75c9e66c07ae19003ab4a66956eac1cb48ea1c2d7ba0b006e5470adb1 +size 1979924992 diff --git a/LLilmonix3b-v0.4a.Q3_K_L.gguf b/LLilmonix3b-v0.4a.Q3_K_L.gguf new file mode 100644 index 0000000..3a34ae8 --- /dev/null +++ b/LLilmonix3b-v0.4a.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5050f9e4df09814f2c178aa96beea0f4238a3178733eac99b145221171fe8bd +size 2214548992 diff --git a/LLilmonix3b-v0.4a.Q3_K_M.gguf b/LLilmonix3b-v0.4a.Q3_K_M.gguf new file mode 100644 index 0000000..370aa83 --- /dev/null +++ b/LLilmonix3b-v0.4a.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baf6e0d43aa1a0102cd45edd522db0e9a5df72c36aabe30ce7d60ae8f32b4d00 +size 2139348992 diff --git a/LLilmonix3b-v0.4a.Q3_K_S.gguf b/LLilmonix3b-v0.4a.Q3_K_S.gguf new file mode 100644 index 0000000..3ff937e --- /dev/null +++ b/LLilmonix3b-v0.4a.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:082923c1e4e0d05affee788127ef9571d46f109d2023283fd5e5a6996553ba0b +size 1979924992 diff --git a/LLilmonix3b-v0.4a.Q4_K_M.gguf b/LLilmonix3b-v0.4a.Q4_K_M.gguf new file mode 100644 index 0000000..906380c --- /dev/null +++ b/LLilmonix3b-v0.4a.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f2e6b3b79d45d14e532a0c68b373ea6d2506176eb8f63c33cffc832ba5259bf +size 2580116992 diff --git a/LLilmonix3b-v0.4a.Q4_K_S.gguf b/LLilmonix3b-v0.4a.Q4_K_S.gguf new file mode 100644 index 0000000..97e15da --- /dev/null +++ b/LLilmonix3b-v0.4a.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3071a08502fdc89b9d4d928a0d224f92e2c5fcb7e56e99a29df50876d4aa8f1d +size 2403156992 diff --git a/LLilmonix3b-v0.4a.Q5_K_M.gguf b/LLilmonix3b-v0.4a.Q5_K_M.gguf new file mode 100644 index 0000000..6020631 --- /dev/null +++ b/LLilmonix3b-v0.4a.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2330ca71b9d06063232d5ff8f9af3d26d11d9029b064e24e60fe282f8574c66a +size 2757076992 diff --git a/LLilmonix3b-v0.4a.Q5_K_S.gguf b/LLilmonix3b-v0.4a.Q5_K_S.gguf new file mode 100644 index 0000000..eae09a9 --- /dev/null +++ b/LLilmonix3b-v0.4a.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306db55826cf103f8d2c5c1db24e4487ad67eeab823c58223ee81381abc7841b +size 2603156992 diff --git a/LLilmonix3b-v0.4a.Q6_K.gguf b/LLilmonix3b-v0.4a.Q6_K.gguf new file mode 100644 index 0000000..f89d570 --- /dev/null +++ b/LLilmonix3b-v0.4a.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6776fd2bc7aba3364d63617afe57a3d48864279e2a6397374e731813fda80d0 +size 3641876992 diff --git a/LLilmonix3b-v0.4a.Q8_0.gguf b/LLilmonix3b-v0.4a.Q8_0.gguf new file mode 100644 index 0000000..81b75c5 --- /dev/null +++ b/LLilmonix3b-v0.4a.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e458ac2e4ceace7fa8c779f6cfafdca478ac1309de31611314641a0614e53c5c +size 3641876992 diff --git a/LLilmonix3b-v0.4a.f16.gguf b/LLilmonix3b-v0.4a.f16.gguf new file mode 100644 index 0000000..7b91551 --- /dev/null +++ b/LLilmonix3b-v0.4a.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce1571ffb86d1ac8fa1751138c264d53c07570e2e1dfcf9929bbcd32b06e8ed5 +size 6854036992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c47fb31 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: 922-CA/LLilmonix3b-v0.4a +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/922-CA/LLilmonix3b-v0.4a + + +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/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.Q2_K.gguf) | Q2_K | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.Q3_K_S.gguf) | Q3_K_S | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.IQ4_XS.gguf) | IQ4_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.Q4_K_M.gguf) | Q4_K_M | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLilmonix3b-v0.4a-GGUF/resolve/main/LLilmonix3b-v0.4a.f16.gguf) | f16 | 7.0 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +