commit ff7ed907b67cfb64087d890e4e0469b23c497fb2 Author: ModelHub XC Date: Tue Oct 13 22:02:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MCQ-qv-8-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..aa4c54d --- /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 +MCQ-qv-8.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-qv-8.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-qv-8.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-qv-8.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-qv-8.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-qv-8.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-qv-8.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-qv-8.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-qv-8.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-qv-8.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-qv-8.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-qv-8.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MCQ-qv-8.IQ4_XS.gguf b/MCQ-qv-8.IQ4_XS.gguf new file mode 100644 index 0000000..6594a60 --- /dev/null +++ b/MCQ-qv-8.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f068c1fc956d13fa4c65db0f058bc6af9f0bb25ca7959a8da71793dfcacafb6 +size 1753185888 diff --git a/MCQ-qv-8.Q2_K.gguf b/MCQ-qv-8.Q2_K.gguf new file mode 100644 index 0000000..7b41866 --- /dev/null +++ b/MCQ-qv-8.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc32bd1e35c1691caf591c43043fb8bf68774f925e9b829147dda8ba8482e180 +size 1274756704 diff --git a/MCQ-qv-8.Q3_K_L.gguf b/MCQ-qv-8.Q3_K_L.gguf new file mode 100644 index 0000000..e1bae45 --- /dev/null +++ b/MCQ-qv-8.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5dde77436cadb009dd7a3e4d80904f81288c85adc6bbfc3f7ceb0588a42234 +size 1707392608 diff --git a/MCQ-qv-8.Q3_K_M.gguf b/MCQ-qv-8.Q3_K_M.gguf new file mode 100644 index 0000000..18d76f6 --- /dev/null +++ b/MCQ-qv-8.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d50c4757221297ee03d7754eb80c5c16dc3733b7f84bccf1535f9d26e797b370 +size 1590476384 diff --git a/MCQ-qv-8.Q3_K_S.gguf b/MCQ-qv-8.Q3_K_S.gguf new file mode 100644 index 0000000..33db27e --- /dev/null +++ b/MCQ-qv-8.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e1845dcd67bdd229162f14eee2fb4cab8917b1320b70ce498f2416527685b40 +size 1454358112 diff --git a/MCQ-qv-8.Q4_K_M.gguf b/MCQ-qv-8.Q4_K_M.gguf new file mode 100644 index 0000000..3f83d60 --- /dev/null +++ b/MCQ-qv-8.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fed18cd909e7cf2617246b0261337e45e381b848d2f6442e0eeee733e7ca271 +size 1929903712 diff --git a/MCQ-qv-8.Q4_K_S.gguf b/MCQ-qv-8.Q4_K_S.gguf new file mode 100644 index 0000000..63dc18b --- /dev/null +++ b/MCQ-qv-8.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70cd1d19ff540ad7038c2de4a1f1bc0f5e067989c56dc71dd0fcab10fd24fa99 +size 1834384992 diff --git a/MCQ-qv-8.Q5_K_M.gguf b/MCQ-qv-8.Q5_K_M.gguf new file mode 100644 index 0000000..8c378f3 --- /dev/null +++ b/MCQ-qv-8.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fecf1373727796df346c4c3524fadaf8b6b7f7e440fad36cf3daf66374c901d +size 2224815712 diff --git a/MCQ-qv-8.Q5_K_S.gguf b/MCQ-qv-8.Q5_K_S.gguf new file mode 100644 index 0000000..ecabd95 --- /dev/null +++ b/MCQ-qv-8.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0503a2518b1fa2829a364d5359d5f463f45391f11ef618300d2fc94c28393ff +size 2169667168 diff --git a/MCQ-qv-8.Q6_K.gguf b/MCQ-qv-8.Q6_K.gguf new file mode 100644 index 0000000..7c786fe --- /dev/null +++ b/MCQ-qv-8.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:987b176b741e05b1fb7107a64799695e76df455b2686406f0fe1ec0a40b7774d +size 2538159712 diff --git a/MCQ-qv-8.Q8_0.gguf b/MCQ-qv-8.Q8_0.gguf new file mode 100644 index 0000000..83ade33 --- /dev/null +++ b/MCQ-qv-8.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9c0f615fef6c76baca27b6a2530c114ddaa9ab3e04d65b2d3380a4c6cadcb66 +size 3285476960 diff --git a/MCQ-qv-8.f16.gguf b/MCQ-qv-8.f16.gguf new file mode 100644 index 0000000..92b1d07 --- /dev/null +++ b/MCQ-qv-8.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91833586cd229e4e7494765e65d941e64c7c73662e748d1ca27eed3b08d48a6b +size 6178317920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c64be2d --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: beyoru/MCQ-qv-8 +datasets: +- beyoru/Tin_hoc_mcq +language: +- en +- vi +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/beyoru/MCQ-qv-8 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MCQ-qv-8-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/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MCQ-qv-8-GGUF/resolve/main/MCQ-qv-8.f16.gguf) | f16 | 6.3 | 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. + +