commit 1b099fc2b046f333d7240d7fa39a75af3d75b691 Author: ModelHub XC Date: Mon Apr 27 09:00:37 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/whimsy-9b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9b15855 --- /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 +whimsy-9b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.f16.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +whimsy-9b.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..7e60fca --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: lodrick-the-lafted/whimsy-9b +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/lodrick-the-lafted/whimsy-9b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/whimsy-9b-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/whimsy-9b-GGUF/resolve/main/whimsy-9b.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.Q4_0_4_4.gguf) | Q4_0_4_4 | 5.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/whimsy-9b-GGUF/resolve/main/whimsy-9b.f16.gguf) | f16 | 18.6 | 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/whimsy-9b.IQ4_XS.gguf b/whimsy-9b.IQ4_XS.gguf new file mode 100644 index 0000000..f94fae7 --- /dev/null +++ b/whimsy-9b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ce7cf5524b4fbd952ec7f12a287cb446e942975ed3e2fa7dd6130101504beb5 +size 5223171392 diff --git a/whimsy-9b.Q2_K.gguf b/whimsy-9b.Q2_K.gguf new file mode 100644 index 0000000..0bd4626 --- /dev/null +++ b/whimsy-9b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:605df0f8c0319af86a785355fc1af5e79715b13441c60920f160da7aec130f96 +size 3805398336 diff --git a/whimsy-9b.Q3_K_L.gguf b/whimsy-9b.Q3_K_L.gguf new file mode 100644 index 0000000..50a9175 --- /dev/null +++ b/whimsy-9b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c80dc217bd2a184ce0cddc0b992ff293cd7552acc73af844546b22709b37038 +size 5132453184 diff --git a/whimsy-9b.Q3_K_M.gguf b/whimsy-9b.Q3_K_M.gguf new file mode 100644 index 0000000..382bfcc --- /dev/null +++ b/whimsy-9b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83d99a2e55cd18069dbdd73e18f63d644b697cf609157500ba77990f45feade9 +size 4761781568 diff --git a/whimsy-9b.Q3_K_S.gguf b/whimsy-9b.Q3_K_S.gguf new file mode 100644 index 0000000..9049980 --- /dev/null +++ b/whimsy-9b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f79136607705f94afc0381d25f91878af61d5557bf0aa45c6374a2a8813a570 +size 4337665344 diff --git a/whimsy-9b.Q4_0_4_4.gguf b/whimsy-9b.Q4_0_4_4.gguf new file mode 100644 index 0000000..d18f606 --- /dev/null +++ b/whimsy-9b.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22e0a27caa22016882496b09ee082dff5d41f6ff92ef2930747f965efd7baf48 +size 5443142976 diff --git a/whimsy-9b.Q4_K_M.gguf b/whimsy-9b.Q4_K_M.gguf new file mode 100644 index 0000000..4c59c58 --- /dev/null +++ b/whimsy-9b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edbd3c132a238350d167318d989caec8d209b8a066cb857dfa8658159717735b +size 5761058112 diff --git a/whimsy-9b.Q4_K_S.gguf b/whimsy-9b.Q4_K_S.gguf new file mode 100644 index 0000000..758200c --- /dev/null +++ b/whimsy-9b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4702d709d25c7db778ff95a54108b23f6fb67e513dd7d1244c4a188b07757e8f +size 5478925632 diff --git a/whimsy-9b.Q5_K_M.gguf b/whimsy-9b.Q5_K_M.gguf new file mode 100644 index 0000000..d2efc75 --- /dev/null +++ b/whimsy-9b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2423b685538c4a82cd67dd64c98c9c273f4cf076c816fb510cb47db24d461309 +size 6647366976 diff --git a/whimsy-9b.Q5_K_S.gguf b/whimsy-9b.Q5_K_S.gguf new file mode 100644 index 0000000..9817607 --- /dev/null +++ b/whimsy-9b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f5cb684d2ce186e641aed274309f4f68f103a4705af228acc080f33670de3e +size 6483592512 diff --git a/whimsy-9b.Q6_K.gguf b/whimsy-9b.Q6_K.gguf new file mode 100644 index 0000000..51d7dac --- /dev/null +++ b/whimsy-9b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acc1e63273c1d621521dda85ba451e986c9c82c220a31986d0d620c8c1cadec6 +size 7589070144 diff --git a/whimsy-9b.Q8_0.gguf b/whimsy-9b.Q8_0.gguf new file mode 100644 index 0000000..71a562b --- /dev/null +++ b/whimsy-9b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31189e43b5dc903291441e7eb413d099eaa4abdcabf63be6e38bae82226e6367 +size 9827149120 diff --git a/whimsy-9b.f16.gguf b/whimsy-9b.f16.gguf new file mode 100644 index 0000000..bb1e856 --- /dev/null +++ b/whimsy-9b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef089331368224f35c26b31b49431e4993fa085692c435c8e853547ac4f67782 +size 18490680640