commit 4912d4018ad397b329e0c9a356374e1a7d2f15e8 Author: ModelHub XC Date: Wed May 6 15:45:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a7a4fe0 --- /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 +QVikhr-2.5-1.5B-Instruct-r.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-2.5-1.5B-Instruct-r.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-2.5-1.5B-Instruct-r.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-2.5-1.5B-Instruct-r.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-2.5-1.5B-Instruct-r.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-2.5-1.5B-Instruct-r.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-2.5-1.5B-Instruct-r.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-2.5-1.5B-Instruct-r.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-2.5-1.5B-Instruct-r.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-2.5-1.5B-Instruct-r.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-2.5-1.5B-Instruct-r.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-2.5-1.5B-Instruct-r.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QVikhr-2.5-1.5B-Instruct-r.IQ4_XS.gguf b/QVikhr-2.5-1.5B-Instruct-r.IQ4_XS.gguf new file mode 100644 index 0000000..dcfc2e2 --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:486b7673a4f8a3801020940575c52af67cdd97d41cbf3d3dbe25faac9954af5c +size 901836032 diff --git a/QVikhr-2.5-1.5B-Instruct-r.Q2_K.gguf b/QVikhr-2.5-1.5B-Instruct-r.Q2_K.gguf new file mode 100644 index 0000000..6092105 --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b075f975cba1034cc28bf780281262876f551f3a331d51fd354750acca9f81 +size 675958016 diff --git a/QVikhr-2.5-1.5B-Instruct-r.Q3_K_L.gguf b/QVikhr-2.5-1.5B-Instruct-r.Q3_K_L.gguf new file mode 100644 index 0000000..97106eb --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee83e65f7d3eca936b5062aaeef57531d8e9fd25a9aecb5f54b3d6fae1c30b68 +size 879815936 diff --git a/QVikhr-2.5-1.5B-Instruct-r.Q3_K_M.gguf b/QVikhr-2.5-1.5B-Instruct-r.Q3_K_M.gguf new file mode 100644 index 0000000..a33ccd7 --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22820aeeead3136b8f2958dfc3ccac0f3e360e4998f86bf993407b7b6550ec83 +size 823831808 diff --git a/QVikhr-2.5-1.5B-Instruct-r.Q3_K_S.gguf b/QVikhr-2.5-1.5B-Instruct-r.Q3_K_S.gguf new file mode 100644 index 0000000..d6dbc74 --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb3b647d75ec3b4721c65050eefeedff6ae23f8da16d1e57ac81c01804fce11 +size 760597760 diff --git a/QVikhr-2.5-1.5B-Instruct-r.Q4_K_M.gguf b/QVikhr-2.5-1.5B-Instruct-r.Q4_K_M.gguf new file mode 100644 index 0000000..9c804fd --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5751ef58aa608125d7508a4ced0af67332506634916fdbe9ff0793dc47f13d6d +size 985701632 diff --git a/QVikhr-2.5-1.5B-Instruct-r.Q4_K_S.gguf b/QVikhr-2.5-1.5B-Instruct-r.Q4_K_S.gguf new file mode 100644 index 0000000..1afbe3d --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e150a1e31cab4fdd859508138bdb419311ee1809da5c0be63db8a465916bc639 +size 939965696 diff --git a/QVikhr-2.5-1.5B-Instruct-r.Q5_K_M.gguf b/QVikhr-2.5-1.5B-Instruct-r.Q5_K_M.gguf new file mode 100644 index 0000000..bac2dfe --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f17b127006a1a68b00d7f79c124500fd2662565913ec21fa262f6aff171196c +size 1124703488 diff --git a/QVikhr-2.5-1.5B-Instruct-r.Q5_K_S.gguf b/QVikhr-2.5-1.5B-Instruct-r.Q5_K_S.gguf new file mode 100644 index 0000000..d10a4bb --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f2694e4197152e9de1c3def6be5e8f70067e4a9bc836b273b29919bc4824bd3 +size 1098382592 diff --git a/QVikhr-2.5-1.5B-Instruct-r.Q6_K.gguf b/QVikhr-2.5-1.5B-Instruct-r.Q6_K.gguf new file mode 100644 index 0000000..4ec2276 --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a10978e41fb52ea401e9ff9c4a2166119c9df2c3c51c57d27bb05bf8cec790 +size 1272392960 diff --git a/QVikhr-2.5-1.5B-Instruct-r.Q8_0.gguf b/QVikhr-2.5-1.5B-Instruct-r.Q8_0.gguf new file mode 100644 index 0000000..4203be1 --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2698c421a15e6f5305841f30c0387872cb9327c8c3b8051d54358889200f0a89 +size 1646125344 diff --git a/QVikhr-2.5-1.5B-Instruct-r.f16.gguf b/QVikhr-2.5-1.5B-Instruct-r.f16.gguf new file mode 100644 index 0000000..d8ff9b1 --- /dev/null +++ b/QVikhr-2.5-1.5B-Instruct-r.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e200773a522f326721a3956c171af0fb37696a812b8ed4f176c90d8a9fdf0a +size 3092831424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..84189f7 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r +datasets: +- Vikhrmodels/russian_math +- openai/gsm8k +language: +- ru +- en +library_name: transformers +license: apache-2.0 +model_name: Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r + + +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/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-2.5-1.5B-Instruct-r-GGUF/resolve/main/QVikhr-2.5-1.5B-Instruct-r.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. + +