commit 5a829be1a40a5d407e55d791fe3356d9d8f6eeab Author: ModelHub XC Date: Wed Apr 22 15:02:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ChatWaifu_v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9b46225 --- /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 +ChatWaifu_v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ChatWaifu_v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ChatWaifu_v1.0.IQ3_M.gguf b/ChatWaifu_v1.0.IQ3_M.gguf new file mode 100644 index 0000000..56bc0d8 --- /dev/null +++ b/ChatWaifu_v1.0.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0472fe044360845e3647cd1d63fd6751eb050e6eed4d9d70d4b24d4c5244a0a +size 3284892384 diff --git a/ChatWaifu_v1.0.IQ3_S.gguf b/ChatWaifu_v1.0.IQ3_S.gguf new file mode 100644 index 0000000..9283c42 --- /dev/null +++ b/ChatWaifu_v1.0.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4f2a4cf8194ebdd82275e51a2238787320dcc6ed74b7aaec40a4245d9e29452 +size 3182394080 diff --git a/ChatWaifu_v1.0.IQ3_XS.gguf b/ChatWaifu_v1.0.IQ3_XS.gguf new file mode 100644 index 0000000..9c97164 --- /dev/null +++ b/ChatWaifu_v1.0.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a32e0b5a84604fc4058e9c71ebed1eba37e02401052c74071f22cc6b8a2cdd1 +size 3018816224 diff --git a/ChatWaifu_v1.0.IQ4_XS.gguf b/ChatWaifu_v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..fb03033 --- /dev/null +++ b/ChatWaifu_v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf96f4c679a8137af3324e5970ddc2abe39615c25501207ad9af2db24aad20ec +size 3944389344 diff --git a/ChatWaifu_v1.0.Q2_K.gguf b/ChatWaifu_v1.0.Q2_K.gguf new file mode 100644 index 0000000..d0de896 --- /dev/null +++ b/ChatWaifu_v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db4ea4384901ea62add9350947aadb58439f6e7e7d6e2fd062c02dbdb44d86bc +size 2719242976 diff --git a/ChatWaifu_v1.0.Q3_K_L.gguf b/ChatWaifu_v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..fcb52b3 --- /dev/null +++ b/ChatWaifu_v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ebe9c22c7d10cad6d9a97733aa327ac9c7eb2c8b7263f746fbe32c4466df38b +size 3822025440 diff --git a/ChatWaifu_v1.0.Q3_K_M.gguf b/ChatWaifu_v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..f463086 --- /dev/null +++ b/ChatWaifu_v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f4286a9ad2a646b00bd912d86062c3dd646638dfdb95c86db68d989aec16caa +size 3518986976 diff --git a/ChatWaifu_v1.0.Q3_K_S.gguf b/ChatWaifu_v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..1daf7b3 --- /dev/null +++ b/ChatWaifu_v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5a17ea8065ca44ea6e264eb2ac671095f32d4ba7dba9b3ede0b952d4d89747 +size 3164568288 diff --git a/ChatWaifu_v1.0.Q4_K_M.gguf b/ChatWaifu_v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..06ae40a --- /dev/null +++ b/ChatWaifu_v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5a98fc1395fd5877be6405e8e43b470ed8c3add87d95b340d65f6c8fa60e268 +size 4368440032 diff --git a/ChatWaifu_v1.0.Q4_K_S.gguf b/ChatWaifu_v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..a8723ac --- /dev/null +++ b/ChatWaifu_v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e87dca06f946553309c420a3427e655ba1fdac4cb9f3ad43f2ba5a3ba269360 +size 4140374752 diff --git a/ChatWaifu_v1.0.Q5_K_M.gguf b/ChatWaifu_v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..21cde6c --- /dev/null +++ b/ChatWaifu_v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:587dabbc0ced40a55a07846bafb02d08f009e49f2913923de6a05231dd41f2ce +size 5131410144 diff --git a/ChatWaifu_v1.0.Q5_K_S.gguf b/ChatWaifu_v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..3912012 --- /dev/null +++ b/ChatWaifu_v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228c3fd1fdae365fea41f750807b0ddee07ea71bbcf810c38cb0402096651cd6 +size 4997716704 diff --git a/ChatWaifu_v1.0.Q6_K.gguf b/ChatWaifu_v1.0.Q6_K.gguf new file mode 100644 index 0000000..d9d06f9 --- /dev/null +++ b/ChatWaifu_v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d897577cb87fea46991d60e8f00224936790201fcac2674f3583c3ae721e544 +size 5942065888 diff --git a/ChatWaifu_v1.0.Q8_0.gguf b/ChatWaifu_v1.0.Q8_0.gguf new file mode 100644 index 0000000..a59cbad --- /dev/null +++ b/ChatWaifu_v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:554c64ca5c901fabc0d28cc7c1165d715787981ba50ca94ae180dcb2e39573c5 +size 7695858400 diff --git a/ChatWaifu_v1.0.f16.gguf b/ChatWaifu_v1.0.f16.gguf new file mode 100644 index 0000000..bd80f44 --- /dev/null +++ b/ChatWaifu_v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a3b5277dfaa32a5c9733c3e11faf332dd8a2298939c7e8a06b8db04ac2ceb2e +size 14484732640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cfbb088 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: spow12/ChatWaifu_v1.0 +language: +- ja +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- nsfw +- Visual novel +- roleplay +--- +## About + + + + + + +static quants of https://huggingface.co/spow12/ChatWaifu_v1.0 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ChatWaifu_v1.0-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/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.IQ3_XS.gguf) | IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ChatWaifu_v1.0-GGUF/resolve/main/ChatWaifu_v1.0.f16.gguf) | f16 | 14.6 | 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. + +