commit c11a7ed1b3a00b61fe49290539cb5e109fc14e6e Author: ModelHub XC Date: Sat Apr 25 10:55:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MCQ-o16-2048-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a1131ff --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-o16-2048.f16.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-o16-2048.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MCQ-o16-2048.IQ4_XS.gguf b/MCQ-o16-2048.IQ4_XS.gguf new file mode 100644 index 0000000..1a53f2e --- /dev/null +++ b/MCQ-o16-2048.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6979b8442084c3bf5227f41a7423c783ae89be3a5193f2ddec142cef7829316 +size 1753185696 diff --git a/MCQ-o16-2048.Q2_K.gguf b/MCQ-o16-2048.Q2_K.gguf new file mode 100644 index 0000000..df9b685 --- /dev/null +++ b/MCQ-o16-2048.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27b9cdd4930cf5e7a96301b8ebe15898129b3ad366428ceba23cdfdbcf33954 +size 1274756512 diff --git a/MCQ-o16-2048.Q3_K_L.gguf b/MCQ-o16-2048.Q3_K_L.gguf new file mode 100644 index 0000000..86d71d5 --- /dev/null +++ b/MCQ-o16-2048.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d7f7ddba78d7a2d218830bbd82b29c3fa9ddcef6981fa1edbb4fc5b740bb7e0 +size 1707392416 diff --git a/MCQ-o16-2048.Q3_K_M.gguf b/MCQ-o16-2048.Q3_K_M.gguf new file mode 100644 index 0000000..6d569bc --- /dev/null +++ b/MCQ-o16-2048.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9be5bdf9aebf0a0ff293e4fa1e686b762501c8e65484320fcd48045b7636cf93 +size 1590476192 diff --git a/MCQ-o16-2048.Q3_K_S.gguf b/MCQ-o16-2048.Q3_K_S.gguf new file mode 100644 index 0000000..e69b663 --- /dev/null +++ b/MCQ-o16-2048.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48d4abf96c8d972e55ceef49390d21b9144e27aec130bbac3c772b64211f150d +size 1454357920 diff --git a/MCQ-o16-2048.Q4_0_4_4.gguf b/MCQ-o16-2048.Q4_0_4_4.gguf new file mode 100644 index 0000000..7f12c3d --- /dev/null +++ b/MCQ-o16-2048.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc4ecaed15a0db1537c27fe16846d0ce33db2f570f795b940dabb06e2d114a64 +size 1822850464 diff --git a/MCQ-o16-2048.Q4_K_M.gguf b/MCQ-o16-2048.Q4_K_M.gguf new file mode 100644 index 0000000..a105273 --- /dev/null +++ b/MCQ-o16-2048.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ebdb46467896fdacfc1203400397339d619792dbf001dbced381c08d8d86590 +size 1929903520 diff --git a/MCQ-o16-2048.Q4_K_S.gguf b/MCQ-o16-2048.Q4_K_S.gguf new file mode 100644 index 0000000..5119877 --- /dev/null +++ b/MCQ-o16-2048.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41546412a577c4f7fa056e52fe40446e9782d19109512c342498c6ce10a66c93 +size 1834384800 diff --git a/MCQ-o16-2048.Q5_K_M.gguf b/MCQ-o16-2048.Q5_K_M.gguf new file mode 100644 index 0000000..713987e --- /dev/null +++ b/MCQ-o16-2048.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02fcd275dead610b5f4a7076825cfbab023b689f70dd9804ac27bb903e053d7 +size 2224815520 diff --git a/MCQ-o16-2048.Q5_K_S.gguf b/MCQ-o16-2048.Q5_K_S.gguf new file mode 100644 index 0000000..f7fa0a9 --- /dev/null +++ b/MCQ-o16-2048.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8192182f14eae07b222439271cbac7491b71876500e9c2adcc9a59ef243662fe +size 2169666976 diff --git a/MCQ-o16-2048.Q6_K.gguf b/MCQ-o16-2048.Q6_K.gguf new file mode 100644 index 0000000..a354ee8 --- /dev/null +++ b/MCQ-o16-2048.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:869224d4186e41a60e6246a41043210f441d00751dccda7c19dc22651cffb89c +size 2538159520 diff --git a/MCQ-o16-2048.Q8_0.gguf b/MCQ-o16-2048.Q8_0.gguf new file mode 100644 index 0000000..d72f9bf --- /dev/null +++ b/MCQ-o16-2048.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1728549660dd2a1ff4397ad72cfa54611e3ba9a6a23503dbb5248f0ed0c00c0 +size 3285476768 diff --git a/MCQ-o16-2048.f16.gguf b/MCQ-o16-2048.f16.gguf new file mode 100644 index 0000000..f236302 --- /dev/null +++ b/MCQ-o16-2048.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8685050556276985f76e0c741bf5952f8f380bd86e6d796d8ed66d688acf3320 +size 6178317728 diff --git a/README.md b/README.md new file mode 100644 index 0000000..04907f6 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: beyoru/MCQ-o16-2048 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/beyoru/MCQ-o16-2048 + + +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-o16-2048-GGUF/resolve/main/MCQ-o16-2048.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MCQ-o16-2048-GGUF/resolve/main/MCQ-o16-2048.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +