commit 9cc392b9ba7a3d6d27bd2ece2899072b5dbdc558 Author: ModelHub XC Date: Mon Oct 5 12:01:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Megumi-Chat-7B-v1.4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3f3556c --- /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 +Megumi-Chat-7B-v1.4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Megumi-Chat-7B-v1.4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Megumi-Chat-7B-v1.4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Megumi-Chat-7B-v1.4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Megumi-Chat-7B-v1.4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Megumi-Chat-7B-v1.4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Megumi-Chat-7B-v1.4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Megumi-Chat-7B-v1.4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Megumi-Chat-7B-v1.4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Megumi-Chat-7B-v1.4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Megumi-Chat-7B-v1.4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Megumi-Chat-7B-v1.4.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Megumi-Chat-7B-v1.4.IQ4_XS.gguf b/Megumi-Chat-7B-v1.4.IQ4_XS.gguf new file mode 100644 index 0000000..7296f15 --- /dev/null +++ b/Megumi-Chat-7B-v1.4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78398fd6e3203ecb3a28a7470f1d07636c3caa345cb6e3b9325da4e548382515 +size 3944389536 diff --git a/Megumi-Chat-7B-v1.4.Q2_K.gguf b/Megumi-Chat-7B-v1.4.Q2_K.gguf new file mode 100644 index 0000000..ea540e6 --- /dev/null +++ b/Megumi-Chat-7B-v1.4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda92151689155c2d60333038210925677bfa4d43c0398d3b1765d545ff805fd +size 2719243168 diff --git a/Megumi-Chat-7B-v1.4.Q3_K_L.gguf b/Megumi-Chat-7B-v1.4.Q3_K_L.gguf new file mode 100644 index 0000000..85750c4 --- /dev/null +++ b/Megumi-Chat-7B-v1.4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4276b68108c518850f4475844a6fa3823fdd49d9e8e12c212db2516a35017492 +size 3822025632 diff --git a/Megumi-Chat-7B-v1.4.Q3_K_M.gguf b/Megumi-Chat-7B-v1.4.Q3_K_M.gguf new file mode 100644 index 0000000..a1545c5 --- /dev/null +++ b/Megumi-Chat-7B-v1.4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1076748dcc2458148e61b2aa5b549eaa03e59c98524b4a0e16afe761d27cbe38 +size 3518987168 diff --git a/Megumi-Chat-7B-v1.4.Q3_K_S.gguf b/Megumi-Chat-7B-v1.4.Q3_K_S.gguf new file mode 100644 index 0000000..0a7516b --- /dev/null +++ b/Megumi-Chat-7B-v1.4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9caebd69505a1d47b85de70661a82df115c5db12de37bbeac66f620fc58aef16 +size 3164568480 diff --git a/Megumi-Chat-7B-v1.4.Q4_K_M.gguf b/Megumi-Chat-7B-v1.4.Q4_K_M.gguf new file mode 100644 index 0000000..edb3d0e --- /dev/null +++ b/Megumi-Chat-7B-v1.4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc923abb3723f737b9b0b7ccbf2399de4856fd7cf3eef9680f9e1ee29f4a70a4 +size 4368440224 diff --git a/Megumi-Chat-7B-v1.4.Q4_K_S.gguf b/Megumi-Chat-7B-v1.4.Q4_K_S.gguf new file mode 100644 index 0000000..17a1dd1 --- /dev/null +++ b/Megumi-Chat-7B-v1.4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3808f26c0441016531c99aa9d81b7639458cfeaab8ad108a4d0c5c90948e41 +size 4140374944 diff --git a/Megumi-Chat-7B-v1.4.Q5_K_M.gguf b/Megumi-Chat-7B-v1.4.Q5_K_M.gguf new file mode 100644 index 0000000..b1a5ca2 --- /dev/null +++ b/Megumi-Chat-7B-v1.4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4d94e2c3d7f3ab19d53c895dde5468c5dc861e29e804fddf571eb95b47eeaf2 +size 5131410336 diff --git a/Megumi-Chat-7B-v1.4.Q5_K_S.gguf b/Megumi-Chat-7B-v1.4.Q5_K_S.gguf new file mode 100644 index 0000000..385566a --- /dev/null +++ b/Megumi-Chat-7B-v1.4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b745c4af6015345765f0b80b78dfe6c490d7048ca0637c93f9643fc6c52d8c24 +size 4997716896 diff --git a/Megumi-Chat-7B-v1.4.Q6_K.gguf b/Megumi-Chat-7B-v1.4.Q6_K.gguf new file mode 100644 index 0000000..7339c0f --- /dev/null +++ b/Megumi-Chat-7B-v1.4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c820d5fcb40c5380b0460bce4f6a84d45a6aac1eb3b6f62c10bdd6ad0bc61a9 +size 5942066080 diff --git a/Megumi-Chat-7B-v1.4.Q8_0.gguf b/Megumi-Chat-7B-v1.4.Q8_0.gguf new file mode 100644 index 0000000..b75875b --- /dev/null +++ b/Megumi-Chat-7B-v1.4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54120d01659605538f504a51c8d912558898def6f54fe9139acf32848ef74bf2 +size 7695858592 diff --git a/Megumi-Chat-7B-v1.4.f16.gguf b/Megumi-Chat-7B-v1.4.f16.gguf new file mode 100644 index 0000000..30ac723 --- /dev/null +++ b/Megumi-Chat-7B-v1.4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a3f260b35b54c59042c6489f2653952797362158466843f6e70f8af364654ab +size 14484732832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..15dd56d --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: megumi21/Megumi-Chat-7B-v1.4 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/megumi21/Megumi-Chat-7B-v1.4 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Megumi-Chat-7B-v1.4-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Megumi-Chat-7B-v1.4-GGUF/resolve/main/Megumi-Chat-7B-v1.4.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. + +