commit 9c5eef6d3cb129d7b63fb0d17124a414ea23debb Author: ModelHub XC Date: Tue Jun 2 09:31:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MgGPT0-7B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cc253dd --- /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 +MgGPT0-7B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MgGPT0-7B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MgGPT0-7B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +MgGPT0-7B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MgGPT0-7B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MgGPT0-7B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MgGPT0-7B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MgGPT0-7B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MgGPT0-7B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MgGPT0-7B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MgGPT0-7B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MgGPT0-7B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MgGPT0-7B-Chat.IQ4_XS.gguf b/MgGPT0-7B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..aa231b5 --- /dev/null +++ b/MgGPT0-7B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8998f816f65d605d2020aa0f3d589780fe5d119736fd24611e0f20c48c9206a +size 3718728192 diff --git a/MgGPT0-7B-Chat.Q2_K.gguf b/MgGPT0-7B-Chat.Q2_K.gguf new file mode 100644 index 0000000..e2c0f8a --- /dev/null +++ b/MgGPT0-7B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62d41be9c5992f1240a61713abf7a33f0aad69e382a6465bfb61ad9da754e498 +size 2593425920 diff --git a/MgGPT0-7B-Chat.Q3_K_L.gguf b/MgGPT0-7B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..4357c2d --- /dev/null +++ b/MgGPT0-7B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a218b3c329dfe18937e66c1e36a7f1612f34140c0800416f986a10cb19c3ace1 +size 3662998016 diff --git a/MgGPT0-7B-Chat.Q3_K_M.gguf b/MgGPT0-7B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..b86d9f8 --- /dev/null +++ b/MgGPT0-7B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcb98f2981927c6e26b11ee50b0fbe4cb24f944368c368fdc79ba3495c7b0062 +size 3363891712 diff --git a/MgGPT0-7B-Chat.Q3_K_S.gguf b/MgGPT0-7B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..241dc1c --- /dev/null +++ b/MgGPT0-7B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a64a2087d6dc2226e069ad66ab1cbbc237e422c40ed8df2ced2c974fc16702eb +size 3014191616 diff --git a/MgGPT0-7B-Chat.Q4_K_M.gguf b/MgGPT0-7B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..246c7cd --- /dev/null +++ b/MgGPT0-7B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:795659401dba739e0873f4ae58e93a374dc9717176b3188c89f56c277a5b07ef +size 4153854464 diff --git a/MgGPT0-7B-Chat.Q4_K_S.gguf b/MgGPT0-7B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..1b6b773 --- /dev/null +++ b/MgGPT0-7B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca28264f2c01eaa3d2590b353ca8ffffeb1a9f78355512e5edb8c8384c9b4208 +size 3929590272 diff --git a/MgGPT0-7B-Chat.Q5_K_M.gguf b/MgGPT0-7B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..025392d --- /dev/null +++ b/MgGPT0-7B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed16f347240a95ad096a25490e62b01fda9ce4b5ff6d131ebb9c418b7bbc369b +size 4862560768 diff --git a/MgGPT0-7B-Chat.Q5_K_S.gguf b/MgGPT0-7B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..a53f4a6 --- /dev/null +++ b/MgGPT0-7B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e996acbd5a77c4467fa9bbf356031869ac508e138978ea0e869a424ada14dff0 +size 4731095552 diff --git a/MgGPT0-7B-Chat.Q6_K.gguf b/MgGPT0-7B-Chat.Q6_K.gguf new file mode 100644 index 0000000..acf4d50 --- /dev/null +++ b/MgGPT0-7B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c40dde2e0e2f84f77ad2ca1d04aead87d6e942042491e29a2868825826d60c1d +size 5615561216 diff --git a/MgGPT0-7B-Chat.Q8_0.gguf b/MgGPT0-7B-Chat.Q8_0.gguf new file mode 100644 index 0000000..21cca6d --- /dev/null +++ b/MgGPT0-7B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eab9368866d20b381058129de4878c3d8f89d9fd015325853f1bd6b7ccf7551 +size 7272851968 diff --git a/MgGPT0-7B-Chat.f16.gguf b/MgGPT0-7B-Chat.f16.gguf new file mode 100644 index 0000000..c0b0565 --- /dev/null +++ b/MgGPT0-7B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4febb2215e9a57ae05837cbd571b23d491b53115c4d9b409c646beb26fb465 +size 13688171008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..33a441b --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: MgGPT/MgGPT0-7B-Chat +language: +- ar +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/MgGPT/MgGPT0-7B-Chat + + +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/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.Q3_K_S.gguf) | Q3_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.Q3_K_L.gguf) | Q3_K_L | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.IQ4_XS.gguf) | IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.Q6_K.gguf) | Q6_K | 5.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MgGPT0-7B-Chat-GGUF/resolve/main/MgGPT0-7B-Chat.f16.gguf) | f16 | 13.8 | 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. + +