commit 4704bcd0e1496a65886315379d3c70259813f8b1 Author: ModelHub XC Date: Fri Sep 25 09:03:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/arXivLlama-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..246d768 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +arXivLlama.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.f16.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +arXivLlama.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5d9d8f2 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: kihato/arXivLlama +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/kihato/arXivLlama + + +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/arXivLlama-GGUF/resolve/main/arXivLlama.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/arXivLlama-GGUF/resolve/main/arXivLlama.f16.gguf) | f16 | 13.6 | 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/arXivLlama.IQ3_M.gguf b/arXivLlama.IQ3_M.gguf new file mode 100644 index 0000000..cc05d61 --- /dev/null +++ b/arXivLlama.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5faff7bf5041804496a1b3b7700796bd53a73688d66e0d923cbe9f70b4402f +size 3114876832 diff --git a/arXivLlama.IQ3_S.gguf b/arXivLlama.IQ3_S.gguf new file mode 100644 index 0000000..e5d988b --- /dev/null +++ b/arXivLlama.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d02b24bccb3961ff19ea1bb080bb7b7af15b4998bcdbf420d4e90bb17aa0b142 +size 2948317088 diff --git a/arXivLlama.IQ3_XS.gguf b/arXivLlama.IQ3_XS.gguf new file mode 100644 index 0000000..1811490 --- /dev/null +++ b/arXivLlama.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b24c285fee15fba382d1daa6344dc67bda758c78512571a136dbe1fce65d7f7c +size 2796535712 diff --git a/arXivLlama.IQ4_XS.gguf b/arXivLlama.IQ4_XS.gguf new file mode 100644 index 0000000..99443d9 --- /dev/null +++ b/arXivLlama.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d2ef25a11f8925d7b19d82a264e73368e35e7c2b5249f64ea9ef1b364d3caa +size 3647528864 diff --git a/arXivLlama.Q2_K.gguf b/arXivLlama.Q2_K.gguf new file mode 100644 index 0000000..3a33514 --- /dev/null +++ b/arXivLlama.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:130bd6ba0be69bbab22ace7cff7beea099a52649f13574f392d9d2de883c8f72 +size 2532876192 diff --git a/arXivLlama.Q3_K_L.gguf b/arXivLlama.Q3_K_L.gguf new file mode 100644 index 0000000..84baf66 --- /dev/null +++ b/arXivLlama.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0504ce715964133dc8ee741932ffa912e4e83b6a69116413f281e7246569692b +size 3597123488 diff --git a/arXivLlama.Q3_K_M.gguf b/arXivLlama.Q3_K_M.gguf new file mode 100644 index 0000000..3f43924 --- /dev/null +++ b/arXivLlama.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b452d3c88bc6c2afdd269943fb98d09e287909a7c43904bc2398acc06b72100 +size 3298017184 diff --git a/arXivLlama.Q3_K_S.gguf b/arXivLlama.Q3_K_S.gguf new file mode 100644 index 0000000..dc71c94 --- /dev/null +++ b/arXivLlama.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5f08d064de94e18ca799ad03baf95e58559c1a392383688be04f477990cc3f +size 2948317088 diff --git a/arXivLlama.Q4_K_M.gguf b/arXivLlama.Q4_K_M.gguf new file mode 100644 index 0000000..890deff --- /dev/null +++ b/arXivLlama.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da7422b5a6233742ea2ee9653764a512c92e1e40579624d3e4593b70a5bfab9 +size 4081016736 diff --git a/arXivLlama.Q4_K_S.gguf b/arXivLlama.Q4_K_S.gguf new file mode 100644 index 0000000..12b420e --- /dev/null +++ b/arXivLlama.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07554a090100dfd710a84ab41e02fa1a89e3f82ff5ff9ded3d8644d524ff960 +size 3856752544 diff --git a/arXivLlama.Q5_K_M.gguf b/arXivLlama.Q5_K_M.gguf new file mode 100644 index 0000000..cbdafe6 --- /dev/null +++ b/arXivLlama.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb5a5287fff01a9c387784cc5decf65d063b55c7048cc608f7b9f2e763b13786 +size 4783169440 diff --git a/arXivLlama.Q5_K_S.gguf b/arXivLlama.Q5_K_S.gguf new file mode 100644 index 0000000..b60689e --- /dev/null +++ b/arXivLlama.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc48bc83f99b4cfa15ccff7d43e51cff235fb7c647c75b1ac47d429f9302f3bb +size 4651704224 diff --git a/arXivLlama.Q6_K.gguf b/arXivLlama.Q6_K.gguf new file mode 100644 index 0000000..2278ef4 --- /dev/null +++ b/arXivLlama.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b085d765de60ec194e8bbb5cf704110124f612b6aa2c6c8a0fc76dfd5fd2ab43 +size 5529206688 diff --git a/arXivLlama.Q8_0.gguf b/arXivLlama.Q8_0.gguf new file mode 100644 index 0000000..76f9524 --- /dev/null +++ b/arXivLlama.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de215635b59bedd5b629142259ea6ca75abc7784918dd4a8ba78957d6f69120a +size 7161102240 diff --git a/arXivLlama.f16.gguf b/arXivLlama.f16.gguf new file mode 100644 index 0000000..40eebb2 --- /dev/null +++ b/arXivLlama.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb00d61931d188b100280175ad53560b2f187afd18bafca7b51a060ca644e9b0 +size 13478117280