commit 5ef7b946a263a7022e58218b9bfbb133944bbccb Author: ModelHub XC Date: Thu Jul 9 20:09:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Monika-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7606842 --- /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 +Monika-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Monika-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Monika-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Monika-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Monika-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Monika-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Monika-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Monika-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Monika-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Monika-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Monika-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Monika-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Monika-8B.IQ4_XS.gguf b/Monika-8B.IQ4_XS.gguf new file mode 100644 index 0000000..ddd17ed --- /dev/null +++ b/Monika-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb51680fa1ce2e83dd457caba13092524f74bf5735862ac47efcec0af0c1dc4 +size 4484368288 diff --git a/Monika-8B.Q2_K.gguf b/Monika-8B.Q2_K.gguf new file mode 100644 index 0000000..b86cc00 --- /dev/null +++ b/Monika-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476185acc457e0b8abb4e0e7bc91c9a72c2a73f7397e0a5d3fae5554d2962171 +size 3179136928 diff --git a/Monika-8B.Q3_K_L.gguf b/Monika-8B.Q3_K_L.gguf new file mode 100644 index 0000000..15c132e --- /dev/null +++ b/Monika-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5501de5c43bc116d319fdc9e84134394cc7e6c296b52729f6551d532ab7a0b9a +size 4321961888 diff --git a/Monika-8B.Q3_K_M.gguf b/Monika-8B.Q3_K_M.gguf new file mode 100644 index 0000000..f8a6b5d --- /dev/null +++ b/Monika-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342efc4d190d35ddd393c5c7c245d79e258aeb92889e52a16897f1899f9788d5 +size 4018923424 diff --git a/Monika-8B.Q3_K_S.gguf b/Monika-8B.Q3_K_S.gguf new file mode 100644 index 0000000..7e83ebd --- /dev/null +++ b/Monika-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37cdb5b85783987c677bfa3569245522934f0cb0a04f83e3b0104a3d0d97d11d +size 3664504736 diff --git a/Monika-8B.Q4_K_M.gguf b/Monika-8B.Q4_K_M.gguf new file mode 100644 index 0000000..a817755 --- /dev/null +++ b/Monika-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7525a6b4f35c55cca94484a8bdc8e5d81ab0948c7ccbb8dfefe8886c984ca836 +size 4920739744 diff --git a/Monika-8B.Q4_K_S.gguf b/Monika-8B.Q4_K_S.gguf new file mode 100644 index 0000000..52f024d --- /dev/null +++ b/Monika-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a9ffc590d860b3558a02b70411bd0dc4f9056cce101017933e98e8cb0e841d3 +size 4692674464 diff --git a/Monika-8B.Q5_K_M.gguf b/Monika-8B.Q5_K_M.gguf new file mode 100644 index 0000000..cf8be97 --- /dev/null +++ b/Monika-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0443b11930ea395cc3afe6452508a095805d3a6ea2aa922abcebc6f4850d954 +size 5732992928 diff --git a/Monika-8B.Q5_K_S.gguf b/Monika-8B.Q5_K_S.gguf new file mode 100644 index 0000000..4349704 --- /dev/null +++ b/Monika-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967782aac8af7fb27ad0f08cba2dac3de643b1d0ffe7d7d387170b0a88c38ae5 +size 5599299488 diff --git a/Monika-8B.Q6_K.gguf b/Monika-8B.Q6_K.gguf new file mode 100644 index 0000000..aabb26b --- /dev/null +++ b/Monika-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9acd26df4eb8aa3ab9461871531e41aceb794efca7e812b01d3fadcf41e29a +size 6596011936 diff --git a/Monika-8B.Q8_0.gguf b/Monika-8B.Q8_0.gguf new file mode 100644 index 0000000..cf2469c --- /dev/null +++ b/Monika-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:147511acd4472ca4a97351b596c39e18478cec04ff1f37705b78a5cfd17e6a48 +size 8540776352 diff --git a/Monika-8B.f16.gguf b/Monika-8B.f16.gguf new file mode 100644 index 0000000..40eccee --- /dev/null +++ b/Monika-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0403caf3289966f701bbbe3e2de4b57f7568fe60c6c55ac1f77f975c30da864c +size 16068896672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..146146c --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Green-eyedDevil/Monika-8B +language: +- en +library_name: transformers +license: llama3.3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- roleplay +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Green-eyedDevil/Monika-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Monika-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Monika-8B-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/Monika-8B-GGUF/resolve/main/Monika-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Monika-8B-GGUF/resolve/main/Monika-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Monika-8B-GGUF/resolve/main/Monika-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Monika-8B-GGUF/resolve/main/Monika-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Monika-8B-GGUF/resolve/main/Monika-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Monika-8B-GGUF/resolve/main/Monika-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Monika-8B-GGUF/resolve/main/Monika-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Monika-8B-GGUF/resolve/main/Monika-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Monika-8B-GGUF/resolve/main/Monika-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Monika-8B-GGUF/resolve/main/Monika-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Monika-8B-GGUF/resolve/main/Monika-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Monika-8B-GGUF/resolve/main/Monika-8B.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. + +