commit 06fa1aad7258952a567e5300ed57282bedd948ef Author: ModelHub XC Date: Sun Aug 16 13:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/danbooru-llama-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..db869cd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +danbooru-llama.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.f16.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +danbooru-llama.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f7254da --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: qwopqwop/danbooru-llama +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/qwopqwop/danbooru-llama + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/danbooru-llama-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/danbooru-llama-GGUF/resolve/main/danbooru-llama.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/danbooru-llama-GGUF/resolve/main/danbooru-llama.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/danbooru-llama.IQ4_XS.gguf b/danbooru-llama.IQ4_XS.gguf new file mode 100644 index 0000000..2e4e6da --- /dev/null +++ b/danbooru-llama.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbadfb87a4134d5cc17d6a87550203b3f2093b3162051a82e3c4e411f4e37d27 +size 3647517120 diff --git a/danbooru-llama.Q2_K.gguf b/danbooru-llama.Q2_K.gguf new file mode 100644 index 0000000..c9f1908 --- /dev/null +++ b/danbooru-llama.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14f0df09f9a16b75e7f4a9d57c2d8855973181b639e642ce17798140bab4cb09 +size 2532864448 diff --git a/danbooru-llama.Q3_K_L.gguf b/danbooru-llama.Q3_K_L.gguf new file mode 100644 index 0000000..9482b11 --- /dev/null +++ b/danbooru-llama.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d36834d5d08d758b0c6dd342b825239a2317ae79fec760cbec2b93517d7b57 +size 3597111744 diff --git a/danbooru-llama.Q3_K_M.gguf b/danbooru-llama.Q3_K_M.gguf new file mode 100644 index 0000000..82b4148 --- /dev/null +++ b/danbooru-llama.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:879e7ecb94c00169b842566de857801f3a724095013d629841f2fdd620a489c9 +size 3298005440 diff --git a/danbooru-llama.Q3_K_S.gguf b/danbooru-llama.Q3_K_S.gguf new file mode 100644 index 0000000..ab3dfe3 --- /dev/null +++ b/danbooru-llama.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbea0c627ff0e46b692cf17152792ebf0ec51f83f8deda222fac7935d966d7d2 +size 2948305344 diff --git a/danbooru-llama.Q4_0_4_4.gguf b/danbooru-llama.Q4_0_4_4.gguf new file mode 100644 index 0000000..54a68d5 --- /dev/null +++ b/danbooru-llama.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30945234e24ccd4a45a85ecf2202015f49e101e524d8a5aa01e9813e7c6bdcf3 +size 3825807808 diff --git a/danbooru-llama.Q4_K_M.gguf b/danbooru-llama.Q4_K_M.gguf new file mode 100644 index 0000000..556fda4 --- /dev/null +++ b/danbooru-llama.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf12de82c3c220657c0530f2cffa2e6c483aff949a4dea2d24e011a3116bd2c8 +size 4081004992 diff --git a/danbooru-llama.Q4_K_S.gguf b/danbooru-llama.Q4_K_S.gguf new file mode 100644 index 0000000..1d69706 --- /dev/null +++ b/danbooru-llama.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:459dd1ea30529c333531a45a748b788b3f08a463d1d62b1ae0c52c24851e7e94 +size 3856740800 diff --git a/danbooru-llama.Q5_K_M.gguf b/danbooru-llama.Q5_K_M.gguf new file mode 100644 index 0000000..35b108f --- /dev/null +++ b/danbooru-llama.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47110c0e19c162fa23128fb039db1c762ece8c329132739caded47fd25b69129 +size 4783157696 diff --git a/danbooru-llama.Q5_K_S.gguf b/danbooru-llama.Q5_K_S.gguf new file mode 100644 index 0000000..b251604 --- /dev/null +++ b/danbooru-llama.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e722d68af0679c66e61463129aee2afc189cd90fd10adea02e357af25192deb +size 4651692480 diff --git a/danbooru-llama.Q6_K.gguf b/danbooru-llama.Q6_K.gguf new file mode 100644 index 0000000..b75795e --- /dev/null +++ b/danbooru-llama.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf5c0d80dfb78d9d487d01240e1f4eb4ed0f5527887ca62ab5bc2fe5b73d05b1 +size 5529194944 diff --git a/danbooru-llama.Q8_0.gguf b/danbooru-llama.Q8_0.gguf new file mode 100644 index 0000000..47e3bc1 --- /dev/null +++ b/danbooru-llama.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f14a6656e43a3d3cd5969b9e544ae21c9bf3b8513fd9d19987ae06c31e0a4d4 +size 7161090496 diff --git a/danbooru-llama.f16.gguf b/danbooru-llama.f16.gguf new file mode 100644 index 0000000..086bd48 --- /dev/null +++ b/danbooru-llama.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657fd928b7cdbf4a02d3fe540415552553b0bcec74898ae39f4a5276dfbdf517 +size 13478105536