commit 5b6dc3a26c8e6e7dbd14bad357c0f4405176b8e3 Author: ModelHub XC Date: Sun Jun 21 15:39:36 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Lazarus-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5b4a265 --- /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 +Lazarus.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Lazarus.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Lazarus.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Lazarus.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lazarus.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lazarus.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lazarus.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lazarus.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lazarus.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lazarus.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Lazarus.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Lazarus.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Lazarus.IQ4_XS.gguf b/Lazarus.IQ4_XS.gguf new file mode 100644 index 0000000..abbc96c --- /dev/null +++ b/Lazarus.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c47a2e34754eaa3febff92a13fd41e89fa906c6243ebc42eef4f2a4fa6a32ec +size 82558976 diff --git a/Lazarus.Q2_K.gguf b/Lazarus.Q2_K.gguf new file mode 100644 index 0000000..6112b92 --- /dev/null +++ b/Lazarus.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5d58d02e8d714a12138a2c7eae9bf39dfe1516ebf0602e960b6595d241a18ab +size 68532224 diff --git a/Lazarus.Q3_K_L.gguf b/Lazarus.Q3_K_L.gguf new file mode 100644 index 0000000..a46bc0c --- /dev/null +++ b/Lazarus.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3228e132c6b6a189fc5ff3ddeca72bd2f0fdb3ddb8da7bc0686243590e656b9 +size 85508096 diff --git a/Lazarus.Q3_K_M.gguf b/Lazarus.Q3_K_M.gguf new file mode 100644 index 0000000..cec7b95 --- /dev/null +++ b/Lazarus.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d916395a79b9fd6aa57afdb59512cb6debe39b59bb0ad0389a73c44ea6aa1a0 +size 81084416 diff --git a/Lazarus.Q3_K_S.gguf b/Lazarus.Q3_K_S.gguf new file mode 100644 index 0000000..67b09f2 --- /dev/null +++ b/Lazarus.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4f184539c865698d87d444e2f34350a8175b66c760f41c5887b39ee928666e +size 73564160 diff --git a/Lazarus.Q4_K_M.gguf b/Lazarus.Q4_K_M.gguf new file mode 100644 index 0000000..438abc9 --- /dev/null +++ b/Lazarus.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeba7c20d313963a64c2420af4dc801c3294db4938184a26a8b6fc8a46962470 +size 91148288 diff --git a/Lazarus.Q4_K_S.gguf b/Lazarus.Q4_K_S.gguf new file mode 100644 index 0000000..34ec909 --- /dev/null +++ b/Lazarus.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34cf4a435da7bf9b779ee37dc5e2564ecd6254f4d6b172e260f5e85aaf309589 +size 85139456 diff --git a/Lazarus.Q5_K_M.gguf b/Lazarus.Q5_K_M.gguf new file mode 100644 index 0000000..d856049 --- /dev/null +++ b/Lazarus.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b884936f9d193f248882a632216e7aa5c631bf7cf1f90c9e01b8080106a453e4 +size 100161536 diff --git a/Lazarus.Q5_K_S.gguf b/Lazarus.Q5_K_S.gguf new file mode 100644 index 0000000..c26b181 --- /dev/null +++ b/Lazarus.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac7b640eeee024936779e57eed51b56d6017b5d170db3337b9060a793b36a627 +size 95461376 diff --git a/Lazarus.Q6_K.gguf b/Lazarus.Q6_K.gguf new file mode 100644 index 0000000..150a9e9 --- /dev/null +++ b/Lazarus.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:997570e30ac5f859143a39f4e11775f088fb983ad23cca1c1c18cfe5f18b62a5 +size 106741760 diff --git a/Lazarus.Q8_0.gguf b/Lazarus.Q8_0.gguf new file mode 100644 index 0000000..fae4048 --- /dev/null +++ b/Lazarus.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32089f521d54f191aede9afde7dee8cccf37ec9ec008b5bc57c185512fc5f99e +size 136659680 diff --git a/Lazarus.f16.gguf b/Lazarus.f16.gguf new file mode 100644 index 0000000..fc1034f --- /dev/null +++ b/Lazarus.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4985fe21268e48cd4d1ad8b8316c20869b53a671ed6fac400516a8490f388957 +size 252470944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c48a6f3 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Aclevo/AclevoGPT-100M-Instruct +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- gpt2 +- distilled +- small-llm +- llama3 +- alpaca +- reasoning +- chatbot +- conversational +--- +## About + + + + + + +static quants of https://huggingface.co/Aclevo/AclevoGPT-100M-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Lazarus-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/Lazarus-GGUF/resolve/main/Lazarus.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Lazarus-GGUF/resolve/main/Lazarus.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Lazarus-GGUF/resolve/main/Lazarus.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Lazarus-GGUF/resolve/main/Lazarus.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Lazarus-GGUF/resolve/main/Lazarus.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lazarus-GGUF/resolve/main/Lazarus.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Lazarus-GGUF/resolve/main/Lazarus.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lazarus-GGUF/resolve/main/Lazarus.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Lazarus-GGUF/resolve/main/Lazarus.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Lazarus-GGUF/resolve/main/Lazarus.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Lazarus-GGUF/resolve/main/Lazarus.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Lazarus-GGUF/resolve/main/Lazarus.f16.gguf) | f16 | 0.4 | 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. + +