commit b4751483c12d4603f754c35186a94365fcf11a68 Author: ModelHub XC Date: Fri Apr 10 22:42:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MCQ-Coder-3B-o-16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..260be69 --- /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-Coder-3B-o-16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.f16.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MCQ-Coder-3B-o-16.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MCQ-Coder-3B-o-16.IQ4_XS.gguf b/MCQ-Coder-3B-o-16.IQ4_XS.gguf new file mode 100644 index 0000000..66c7647 --- /dev/null +++ b/MCQ-Coder-3B-o-16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e04d9950d1d3230f52895c239b5f09c701a3a2ba79e410b90b446a170035672 +size 1753185792 diff --git a/MCQ-Coder-3B-o-16.Q2_K.gguf b/MCQ-Coder-3B-o-16.Q2_K.gguf new file mode 100644 index 0000000..f3a5323 --- /dev/null +++ b/MCQ-Coder-3B-o-16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bca8941f5be48627c1119e251ef5de7b40b28879da44a9cc2bfa48bb4ff54e6 +size 1274756608 diff --git a/MCQ-Coder-3B-o-16.Q3_K_L.gguf b/MCQ-Coder-3B-o-16.Q3_K_L.gguf new file mode 100644 index 0000000..b5981db --- /dev/null +++ b/MCQ-Coder-3B-o-16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d37acab039ef3c98569bfe36b10dbeb33669fe655e94a7d1d0e5d16362d63377 +size 1707392512 diff --git a/MCQ-Coder-3B-o-16.Q3_K_M.gguf b/MCQ-Coder-3B-o-16.Q3_K_M.gguf new file mode 100644 index 0000000..d512c71 --- /dev/null +++ b/MCQ-Coder-3B-o-16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d79cb3b40f22445d865f7507a0013cf1ec56b6e3c10762afb99e3ca3c62086 +size 1590476288 diff --git a/MCQ-Coder-3B-o-16.Q3_K_S.gguf b/MCQ-Coder-3B-o-16.Q3_K_S.gguf new file mode 100644 index 0000000..c4e4177 --- /dev/null +++ b/MCQ-Coder-3B-o-16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fb831e9c067b31f5d0ef36b8e7c6f3a92dd3db92a1c26ab0793fb2a0a409620 +size 1454358016 diff --git a/MCQ-Coder-3B-o-16.Q4_0_4_4.gguf b/MCQ-Coder-3B-o-16.Q4_0_4_4.gguf new file mode 100644 index 0000000..905e917 --- /dev/null +++ b/MCQ-Coder-3B-o-16.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7833ad680b93e9b5c0358a0ff02e9d5632ac1911c0089f8e850b14ec54e524cb +size 1822850560 diff --git a/MCQ-Coder-3B-o-16.Q4_K_M.gguf b/MCQ-Coder-3B-o-16.Q4_K_M.gguf new file mode 100644 index 0000000..ab3e31e --- /dev/null +++ b/MCQ-Coder-3B-o-16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a001452ab7858e7b40301d78e87d4d25cec499d789ed5dcb1b66ba014e9a35f +size 1929903616 diff --git a/MCQ-Coder-3B-o-16.Q4_K_S.gguf b/MCQ-Coder-3B-o-16.Q4_K_S.gguf new file mode 100644 index 0000000..c06f874 --- /dev/null +++ b/MCQ-Coder-3B-o-16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cebc89b2ecdd3caae61cc062932ee5a59bea88a769d376195883c025ec99448 +size 1834384896 diff --git a/MCQ-Coder-3B-o-16.Q5_K_M.gguf b/MCQ-Coder-3B-o-16.Q5_K_M.gguf new file mode 100644 index 0000000..aa5d1fe --- /dev/null +++ b/MCQ-Coder-3B-o-16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5bb9470708bf4ae0ea67b3d2def9ac903fbf1788068228520ec08e12680ed77 +size 2224815616 diff --git a/MCQ-Coder-3B-o-16.Q5_K_S.gguf b/MCQ-Coder-3B-o-16.Q5_K_S.gguf new file mode 100644 index 0000000..575ebc1 --- /dev/null +++ b/MCQ-Coder-3B-o-16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:330c1f4a31022da093c6a91329201b41b7b9f4cf5b57ec9131cfab757c5dd5c9 +size 2169667072 diff --git a/MCQ-Coder-3B-o-16.Q6_K.gguf b/MCQ-Coder-3B-o-16.Q6_K.gguf new file mode 100644 index 0000000..ad2a573 --- /dev/null +++ b/MCQ-Coder-3B-o-16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf4ab516ea88fb73bb545b492fcbc967455860f95f861567b88d328f9f12ad9a +size 2538159616 diff --git a/MCQ-Coder-3B-o-16.Q8_0.gguf b/MCQ-Coder-3B-o-16.Q8_0.gguf new file mode 100644 index 0000000..650dd86 --- /dev/null +++ b/MCQ-Coder-3B-o-16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b624521688e2eca351c6ad9f6d60bc1132516eb65dba71be586798198288fc5 +size 3285476864 diff --git a/MCQ-Coder-3B-o-16.f16.gguf b/MCQ-Coder-3B-o-16.f16.gguf new file mode 100644 index 0000000..68f55d2 --- /dev/null +++ b/MCQ-Coder-3B-o-16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dadeca5f2e18b0021432b6a4f5a4a8a2c978456e3c0e9a9bfe83e2306c2283e +size 6178317824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3110459 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: beyoru/MCQ-Coder-3B-o-16 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/beyoru/MCQ-Coder-3B-o-16 + + +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-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MCQ-Coder-3B-o-16-GGUF/resolve/main/MCQ-Coder-3B-o-16.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. + +