commit 731fd2557edf71870e6b776376ea48bebde01f5a Author: ModelHub XC Date: Thu Jun 18 15:41:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SzilviaB-LongWriter-llama3.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6d5a5ac --- /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 +SzilviaB-LongWriter-llama3.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SzilviaB-LongWriter-llama3.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SzilviaB-LongWriter-llama3.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SzilviaB-LongWriter-llama3.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SzilviaB-LongWriter-llama3.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SzilviaB-LongWriter-llama3.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +SzilviaB-LongWriter-llama3.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SzilviaB-LongWriter-llama3.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SzilviaB-LongWriter-llama3.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SzilviaB-LongWriter-llama3.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SzilviaB-LongWriter-llama3.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SzilviaB-LongWriter-llama3.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f708a5b --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: MrRobotoAI/SzilviaB-LongWriter-llama3.1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/MrRobotoAI/SzilviaB-LongWriter-llama3.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-i1-GGUF +## 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/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SzilviaB-LongWriter-llama3.1-GGUF/resolve/main/SzilviaB-LongWriter-llama3.1.f16.gguf) | f16 | 16.2 | 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/SzilviaB-LongWriter-llama3.1.IQ4_XS.gguf b/SzilviaB-LongWriter-llama3.1.IQ4_XS.gguf new file mode 100644 index 0000000..1dba040 --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78d5d3779a94b3f54c3689f0084025a3660cd114db5d06e0ec904262ae27f257 +size 4484364384 diff --git a/SzilviaB-LongWriter-llama3.1.Q2_K.gguf b/SzilviaB-LongWriter-llama3.1.Q2_K.gguf new file mode 100644 index 0000000..0fbe6d2 --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:606ed977b49cc88b4970dacd0f45c1db1ac80b22546e062f115189a5b43159d6 +size 3179133024 diff --git a/SzilviaB-LongWriter-llama3.1.Q3_K_L.gguf b/SzilviaB-LongWriter-llama3.1.Q3_K_L.gguf new file mode 100644 index 0000000..ab333b7 --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1565715eab20542fc2122acb2a9f0536aee89afc4745b70bf63817569e969c87 +size 4321957984 diff --git a/SzilviaB-LongWriter-llama3.1.Q3_K_M.gguf b/SzilviaB-LongWriter-llama3.1.Q3_K_M.gguf new file mode 100644 index 0000000..f54cb2b --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:663002dc5d83ad1f87b318e96974b9df41b277a8206dbbad897093b943db816e +size 4018919520 diff --git a/SzilviaB-LongWriter-llama3.1.Q3_K_S.gguf b/SzilviaB-LongWriter-llama3.1.Q3_K_S.gguf new file mode 100644 index 0000000..669a08a --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8788f583d59e51e70681347c9db5f0ac9aea0d468c8691691d31a2be6931828f +size 3664500832 diff --git a/SzilviaB-LongWriter-llama3.1.Q4_K_M.gguf b/SzilviaB-LongWriter-llama3.1.Q4_K_M.gguf new file mode 100644 index 0000000..1c80219 --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fd1856b9a12b5f3e8ecf4d042d42a4c86d9a1b637e2a09080690f3e2dc00ade +size 4920735840 diff --git a/SzilviaB-LongWriter-llama3.1.Q4_K_S.gguf b/SzilviaB-LongWriter-llama3.1.Q4_K_S.gguf new file mode 100644 index 0000000..e11ed68 --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e21be8090f49600890dc5a01275a785a0fc879b56c837fcaf2e9162e5accdb45 +size 4692670560 diff --git a/SzilviaB-LongWriter-llama3.1.Q5_K_M.gguf b/SzilviaB-LongWriter-llama3.1.Q5_K_M.gguf new file mode 100644 index 0000000..d4e6a14 --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:092cac049dcb83996fb4c0764cb8086cf025f47940779dfd1056b0b46c6a46db +size 5732989024 diff --git a/SzilviaB-LongWriter-llama3.1.Q5_K_S.gguf b/SzilviaB-LongWriter-llama3.1.Q5_K_S.gguf new file mode 100644 index 0000000..a35f9fd --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:791c32abf4d1cbb0131f7fcbd520982ec722c9217491b1d9e0f6bbba3422ca12 +size 5599295584 diff --git a/SzilviaB-LongWriter-llama3.1.Q6_K.gguf b/SzilviaB-LongWriter-llama3.1.Q6_K.gguf new file mode 100644 index 0000000..1abad98 --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37eb5d0a121ae49aa2a321294d8af98db8ce7932367ec8c6f8c0617ae1ff594b +size 6596008032 diff --git a/SzilviaB-LongWriter-llama3.1.Q8_0.gguf b/SzilviaB-LongWriter-llama3.1.Q8_0.gguf new file mode 100644 index 0000000..f9b862f --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86b502219f161938eec369ad6ff4827058f8391b84ab394cc32a004bb0994367 +size 8540772448 diff --git a/SzilviaB-LongWriter-llama3.1.f16.gguf b/SzilviaB-LongWriter-llama3.1.f16.gguf new file mode 100644 index 0000000..ae58264 --- /dev/null +++ b/SzilviaB-LongWriter-llama3.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ac3a2b5a92d52789f02592694385353fc91bc3c2e9bbd08051b818912cac84e +size 16068892768