commit 83627b080ac1e0f06573dc84c424721f7cc5cb65 Author: ModelHub XC Date: Sat Aug 8 13:12:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MIXdevAI-yandexGPT5-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f3fe0f4 --- /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 +MIXdevAI-yandexGPT5-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MIXdevAI-yandexGPT5-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MIXdevAI-yandexGPT5-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MIXdevAI-yandexGPT5-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MIXdevAI-yandexGPT5-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MIXdevAI-yandexGPT5-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MIXdevAI-yandexGPT5-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MIXdevAI-yandexGPT5-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MIXdevAI-yandexGPT5-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MIXdevAI-yandexGPT5-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MIXdevAI-yandexGPT5-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MIXdevAI-yandexGPT5-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MIXdevAI-yandexGPT5-8B.IQ4_XS.gguf b/MIXdevAI-yandexGPT5-8B.IQ4_XS.gguf new file mode 100644 index 0000000..1937261 --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4366c1199092168d4acd099161894fada3fc7ee000650dd0e2c67231a11680bb +size 4484295360 diff --git a/MIXdevAI-yandexGPT5-8B.Q2_K.gguf b/MIXdevAI-yandexGPT5-8B.Q2_K.gguf new file mode 100644 index 0000000..7b0b013 --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06cf63612831b304a311a6f86d697a08dc05d218f415a904e4efbe69a6b3b14f +size 3178421696 diff --git a/MIXdevAI-yandexGPT5-8B.Q3_K_L.gguf b/MIXdevAI-yandexGPT5-8B.Q3_K_L.gguf new file mode 100644 index 0000000..beb5b8d --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc88ff6b07c148d37a66d873e7202ff068047fe61e31515deec8f4fc32d43204 +size 4321567808 diff --git a/MIXdevAI-yandexGPT5-8B.Q3_K_M.gguf b/MIXdevAI-yandexGPT5-8B.Q3_K_M.gguf new file mode 100644 index 0000000..2ba97fc --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06fc8b8dd55db93067963a60e2f7bf58d68d7ec466a90915e9df0df6d893300e +size 4018529344 diff --git a/MIXdevAI-yandexGPT5-8B.Q3_K_S.gguf b/MIXdevAI-yandexGPT5-8B.Q3_K_S.gguf new file mode 100644 index 0000000..30bfdaf --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90bc96f6499c0bb54a3be4e981182beee68dd8758cc3d35ec28e1cb0bc4afb41 +size 3664110656 diff --git a/MIXdevAI-yandexGPT5-8B.Q4_K_M.gguf b/MIXdevAI-yandexGPT5-8B.Q4_K_M.gguf new file mode 100644 index 0000000..7d5726d --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33bed317ed767121de037af77ca7f1ca3e0a446185b77b11680bc26c5fb2f630 +size 4920765632 diff --git a/MIXdevAI-yandexGPT5-8B.Q4_K_S.gguf b/MIXdevAI-yandexGPT5-8B.Q4_K_S.gguf new file mode 100644 index 0000000..03ea88a --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f48a52d0fecbde77852aff107b7fbdf67330cdb2e4a25f8cbf87d24b785dbfa +size 4692700352 diff --git a/MIXdevAI-yandexGPT5-8B.Q5_K_M.gguf b/MIXdevAI-yandexGPT5-8B.Q5_K_M.gguf new file mode 100644 index 0000000..99673a5 --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f351272ad48843f0330377035b04abb63fe9b4cf28f1defea4ce5f1f9bf709 +size 5733414080 diff --git a/MIXdevAI-yandexGPT5-8B.Q5_K_S.gguf b/MIXdevAI-yandexGPT5-8B.Q5_K_S.gguf new file mode 100644 index 0000000..5d18f70 --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4a17dedb84143c332d6cde0e33fd0f52cffce790e792cd8aff44d80c7f7494 +size 5599720640 diff --git a/MIXdevAI-yandexGPT5-8B.Q6_K.gguf b/MIXdevAI-yandexGPT5-8B.Q6_K.gguf new file mode 100644 index 0000000..da3c132 --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cac3828bbdd00d8beb3514bcf97ff847b25c45fd13002e68479747894051d17b +size 6596853056 diff --git a/MIXdevAI-yandexGPT5-8B.Q8_0.gguf b/MIXdevAI-yandexGPT5-8B.Q8_0.gguf new file mode 100644 index 0000000..080da62 --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:931dfef500cad676b8bc98b628b0ce75ad1ab14eff82a456c2cdd6542bd873b3 +size 8543149120 diff --git a/MIXdevAI-yandexGPT5-8B.f16.gguf b/MIXdevAI-yandexGPT5-8B.f16.gguf new file mode 100644 index 0000000..cc6ca81 --- /dev/null +++ b/MIXdevAI-yandexGPT5-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04a90481328348f111b054ba6a166362fbd7d84aad5ac0b7899f585cc1797ed2 +size 16077198400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..de10b47 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Kolyadual/MIXdevAI-yandexGPT5-8B +language: +- ru +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- yandexgpt +- saiga +- russian +- NewtonBotFamilyTree +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Kolyadual/MIXdevAI-yandexGPT5-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MIXdevAI-yandexGPT5-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-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/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MIXdevAI-yandexGPT5-8B-GGUF/resolve/main/MIXdevAI-yandexGPT5-8B.f16.gguf) | f16 | 16.2 | 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. + +