commit 91d7734574fb7d418593949a541192d44b6f179c Author: ModelHub XC Date: Sun Jun 14 22:16:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/YOTO_1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..699f513 --- /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 +YOTO_1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +YOTO_1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +YOTO_1.f16.gguf filter=lfs diff=lfs merge=lfs -text +YOTO_1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +YOTO_1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +YOTO_1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +YOTO_1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +YOTO_1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +YOTO_1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +YOTO_1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +YOTO_1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +YOTO_1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..acae48b --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: beyoru/YOTO_1 +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/YOTO_1 + + +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/YOTO_1-GGUF/resolve/main/YOTO_1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/YOTO_1-GGUF/resolve/main/YOTO_1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/YOTO_1-GGUF/resolve/main/YOTO_1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/YOTO_1-GGUF/resolve/main/YOTO_1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/YOTO_1-GGUF/resolve/main/YOTO_1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/YOTO_1-GGUF/resolve/main/YOTO_1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/YOTO_1-GGUF/resolve/main/YOTO_1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/YOTO_1-GGUF/resolve/main/YOTO_1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/YOTO_1-GGUF/resolve/main/YOTO_1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/YOTO_1-GGUF/resolve/main/YOTO_1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/YOTO_1-GGUF/resolve/main/YOTO_1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/YOTO_1-GGUF/resolve/main/YOTO_1.f16.gguf) | f16 | 15.3 | 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. + + diff --git a/YOTO_1.IQ4_XS.gguf b/YOTO_1.IQ4_XS.gguf new file mode 100644 index 0000000..14ec7f7 --- /dev/null +++ b/YOTO_1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a7ab0fde8ae70d329968874f2393308637f8f2b0e0da2ed0841f36ba8a76537 +size 4250299232 diff --git a/YOTO_1.Q2_K.gguf b/YOTO_1.Q2_K.gguf new file mode 100644 index 0000000..4c70596 --- /dev/null +++ b/YOTO_1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4da577824cd502643069081c28c6a6cbf655f71f418777db4f0ff0de416ebf +size 3015940960 diff --git a/YOTO_1.Q3_K_L.gguf b/YOTO_1.Q3_K_L.gguf new file mode 100644 index 0000000..67da586 --- /dev/null +++ b/YOTO_1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7b5e92182eed1c8f4c3b4902e2b211c1e21b39bb719aa95e974cad58f83d812 +size 4088460128 diff --git a/YOTO_1.Q3_K_M.gguf b/YOTO_1.Q3_K_M.gguf new file mode 100644 index 0000000..b740268 --- /dev/null +++ b/YOTO_1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea90fd33b581a1163543374f6354d443bfad477a9f1ccd7b513f902ca1315340 +size 3808392032 diff --git a/YOTO_1.Q3_K_S.gguf b/YOTO_1.Q3_K_S.gguf new file mode 100644 index 0000000..0a6872b --- /dev/null +++ b/YOTO_1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b55985dfda6faca9035fbb8c8f97efa9936f20c083a603ab5b6c233dba22df09 +size 3492369248 diff --git a/YOTO_1.Q4_K_M.gguf b/YOTO_1.Q4_K_M.gguf new file mode 100644 index 0000000..c552dd3 --- /dev/null +++ b/YOTO_1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d49795ab94bb061df00a18ec2d05a3edff3e5768d4d3c949e9db995308d44be +size 4683074400 diff --git a/YOTO_1.Q4_K_S.gguf b/YOTO_1.Q4_K_S.gguf new file mode 100644 index 0000000..1506470 --- /dev/null +++ b/YOTO_1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a5b63bf5836fc63de954180f1b0da0779687dbbfc44d6910451dd4758f7b78f +size 4457769824 diff --git a/YOTO_1.Q5_K_M.gguf b/YOTO_1.Q5_K_M.gguf new file mode 100644 index 0000000..bd30903 --- /dev/null +++ b/YOTO_1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2f80c69e7ac5c814c47b5d52f98299a17ffcfe5c0161a412ba7293bd3c8b460 +size 5444832096 diff --git a/YOTO_1.Q5_K_S.gguf b/YOTO_1.Q5_K_S.gguf new file mode 100644 index 0000000..28996de --- /dev/null +++ b/YOTO_1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0615b7e4360e0430d7ae8dc58c9bbac979b896b9f17f4c0d1f6530d37099d846 +size 5315177312 diff --git a/YOTO_1.Q6_K.gguf b/YOTO_1.Q6_K.gguf new file mode 100644 index 0000000..7133015 --- /dev/null +++ b/YOTO_1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:286135f62d6f0f03e4525a2494c5cc98b362c7dfdf53cd4805a985bd95f1f2ce +size 6254199648 diff --git a/YOTO_1.Q8_0.gguf b/YOTO_1.Q8_0.gguf new file mode 100644 index 0000000..f10498d --- /dev/null +++ b/YOTO_1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:791224f9e8ff2bd6b356af64e238a0861aae17ce22577abd1238e1e323a22098 +size 8098526048 diff --git a/YOTO_1.f16.gguf b/YOTO_1.f16.gguf new file mode 100644 index 0000000..63225cf --- /dev/null +++ b/YOTO_1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c89a1df7cf91c36b2f9ee134e7b72c6798c540a9eed3426cf82267a61e0650ab +size 15237854048