commit aba6c72d09bddc85814367057ff366f3e1f59c2e Author: ModelHub XC Date: Sat Jul 11 05:45:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Omni-Reasoner-2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cc7f33f --- /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 +Omni-Reasoner-2B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Omni-Reasoner-2B.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Omni-Reasoner-2B.IQ4_XS.gguf b/Omni-Reasoner-2B.IQ4_XS.gguf new file mode 100644 index 0000000..6e709bd --- /dev/null +++ b/Omni-Reasoner-2B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a00749d4c1c9de990f87e8579a26a6a67049e24f23b7b22ec5e578930ad75a +size 902181920 diff --git a/Omni-Reasoner-2B.Q2_K.gguf b/Omni-Reasoner-2B.Q2_K.gguf new file mode 100644 index 0000000..a12f73c --- /dev/null +++ b/Omni-Reasoner-2B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc802c24bec90120ca0d3bfb2b6f7aa0d10033827b1920b580095acec0ab3af +size 676303904 diff --git a/Omni-Reasoner-2B.Q3_K_L.gguf b/Omni-Reasoner-2B.Q3_K_L.gguf new file mode 100644 index 0000000..c809cff --- /dev/null +++ b/Omni-Reasoner-2B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd93c7c764d8e27328540a07047ea4e3d3f1a3b78457f82bed387b57601e8639 +size 880161824 diff --git a/Omni-Reasoner-2B.Q3_K_M.gguf b/Omni-Reasoner-2B.Q3_K_M.gguf new file mode 100644 index 0000000..7ce9e7e --- /dev/null +++ b/Omni-Reasoner-2B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa29507c1736a84f60eb710e0503f079ce38df2a3a6669fb73e8774a606b0a9a +size 824177696 diff --git a/Omni-Reasoner-2B.Q3_K_S.gguf b/Omni-Reasoner-2B.Q3_K_S.gguf new file mode 100644 index 0000000..117dcbe --- /dev/null +++ b/Omni-Reasoner-2B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c954b5052e1c532a380f4c3e17bed883a720dbb78416f8a4d3e3dc2b6dcd2fd +size 760943648 diff --git a/Omni-Reasoner-2B.Q4_K_M.gguf b/Omni-Reasoner-2B.Q4_K_M.gguf new file mode 100644 index 0000000..b776b9f --- /dev/null +++ b/Omni-Reasoner-2B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0724efe240b95bc14b82527c0bcb9a51fd70d3fcdcd6cf1b6296f6603917d6b0 +size 986047520 diff --git a/Omni-Reasoner-2B.Q4_K_S.gguf b/Omni-Reasoner-2B.Q4_K_S.gguf new file mode 100644 index 0000000..ba08513 --- /dev/null +++ b/Omni-Reasoner-2B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f814295d79343710a0ac1126f32efda9bc9d1460e5c90ee4bac932c57f4960a +size 940311584 diff --git a/Omni-Reasoner-2B.Q5_K_M.gguf b/Omni-Reasoner-2B.Q5_K_M.gguf new file mode 100644 index 0000000..5cb6e56 --- /dev/null +++ b/Omni-Reasoner-2B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:422abe9d3578a4151f14491e04f35eab3ba8e603092ce49a6cc6badf3af022a7 +size 1125049376 diff --git a/Omni-Reasoner-2B.Q5_K_S.gguf b/Omni-Reasoner-2B.Q5_K_S.gguf new file mode 100644 index 0000000..45a5f29 --- /dev/null +++ b/Omni-Reasoner-2B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43eed4d881020efd127bcc968d965c0c9155aded367ec3694bb007fa9d37e841 +size 1098728480 diff --git a/Omni-Reasoner-2B.Q6_K.gguf b/Omni-Reasoner-2B.Q6_K.gguf new file mode 100644 index 0000000..2f5f514 --- /dev/null +++ b/Omni-Reasoner-2B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af994a502969a9631198d8aeb13c701256cdc8b62e92cb39b08d43cd0d72d27e +size 1272738848 diff --git a/Omni-Reasoner-2B.Q8_0.gguf b/Omni-Reasoner-2B.Q8_0.gguf new file mode 100644 index 0000000..8b924d3 --- /dev/null +++ b/Omni-Reasoner-2B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88150c384b25946610e003b4ee7b95fbf87ceb485279c12ae908fac3ff3ea15e +size 1646572064 diff --git a/Omni-Reasoner-2B.f16.gguf b/Omni-Reasoner-2B.f16.gguf new file mode 100644 index 0000000..b836c2e --- /dev/null +++ b/Omni-Reasoner-2B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a7e4f4314c279c300e1373ce3c44913f64947ce24238e54fd904e44446cdfa +size 3093668384 diff --git a/Omni-Reasoner-2B.mmproj-fp16.gguf b/Omni-Reasoner-2B.mmproj-fp16.gguf new file mode 100644 index 0000000..0057c51 --- /dev/null +++ b/Omni-Reasoner-2B.mmproj-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e5d45c0b017b626332ab4b09edc275f30a67cee1d576fe8822862d528cb4cd +size 1331656192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3b1120f --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: prithivMLmods/Omni-Reasoner-2B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- Omni +- Math +- Reasoner +- Qwen-Base +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Omni-Reasoner-2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Omni-Reasoner-2B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Omni-Reasoner-2B-i1-GGUF +## 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/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Omni-Reasoner-2B-GGUF/resolve/main/Omni-Reasoner-2B.f16.gguf) | f16 | 3.2 | 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. + +