commit dc27f3a9ae8453cc29412be7ccad5328471a874e Author: ModelHub XC Date: Sat Apr 11 00:24:59 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Yi-6B-200K-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..357d714 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Yi-6B-200K.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.f16.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5269c70 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: 01-ai/Yi-6B-200K +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/01-ai/Yi-6B-200K + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Yi-6B-200K-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/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.Q2_K.gguf) | Q2_K | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.IQ3_XS.gguf) | IQ3_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.Q3_K_S.gguf) | Q3_K_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.IQ3_S.gguf) | IQ3_S | 2.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.IQ3_M.gguf) | IQ3_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.Q3_K_M.gguf) | Q3_K_M | 3.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.Q3_K_L.gguf) | Q3_K_L | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.IQ4_XS.gguf) | IQ4_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.Q4_K_S.gguf) | Q4_K_S | 3.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.Q4_K_M.gguf) | Q4_K_M | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.Q5_K_S.gguf) | Q5_K_S | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.Q5_K_M.gguf) | Q5_K_M | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.Q6_K.gguf) | Q6_K | 5.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.Q8_0.gguf) | Q8_0 | 6.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-GGUF/resolve/main/Yi-6B-200K.f16.gguf) | f16 | 12.2 | 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. + + diff --git a/Yi-6B-200K.IQ3_M.gguf b/Yi-6B-200K.IQ3_M.gguf new file mode 100644 index 0000000..370eb2e --- /dev/null +++ b/Yi-6B-200K.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:638b9c0f50d109c2a6081d67d256ab0779497079986ec8cf388b2ab8f20499e4 +size 2813366112 diff --git a/Yi-6B-200K.IQ3_S.gguf b/Yi-6B-200K.IQ3_S.gguf new file mode 100644 index 0000000..8ec48aa --- /dev/null +++ b/Yi-6B-200K.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:836bea64e40f4a4f0a815f9639bcfa832732758c53db046a84cf8787b8ed147a +size 2718109536 diff --git a/Yi-6B-200K.IQ3_XS.gguf b/Yi-6B-200K.IQ3_XS.gguf new file mode 100644 index 0000000..360c8c3 --- /dev/null +++ b/Yi-6B-200K.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eee7e17f1e1a946d301ade0b52e0ce4e75b173d71b37a37f4fe5570d662803c +size 2588348256 diff --git a/Yi-6B-200K.IQ4_XS.gguf b/Yi-6B-200K.IQ4_XS.gguf new file mode 100644 index 0000000..73aec66 --- /dev/null +++ b/Yi-6B-200K.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81e9fd839a952d75cd020fd241ac2854a7eeeab3c3db0282eb5ed45294524a16 +size 3336785760 diff --git a/Yi-6B-200K.Q2_K.gguf b/Yi-6B-200K.Q2_K.gguf new file mode 100644 index 0000000..f879fd7 --- /dev/null +++ b/Yi-6B-200K.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:474f0357fd32eda27575be27354210a1acf6cd6a1c608f64112b609a1ebdcade +size 2337066848 diff --git a/Yi-6B-200K.Q3_K_L.gguf b/Yi-6B-200K.Q3_K_L.gguf new file mode 100644 index 0000000..52bd231 --- /dev/null +++ b/Yi-6B-200K.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:299dec2cabeed7d46680b74c7754157cd4a6a873e312c17200793bb1956491ac +size 3236892512 diff --git a/Yi-6B-200K.Q3_K_M.gguf b/Yi-6B-200K.Q3_K_M.gguf new file mode 100644 index 0000000..4849fef --- /dev/null +++ b/Yi-6B-200K.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab02ff128cdb47d7deb66dd53e0ad5683c484ea97f85095d20948f97fe49005e +size 2992836448 diff --git a/Yi-6B-200K.Q3_K_S.gguf b/Yi-6B-200K.Q3_K_S.gguf new file mode 100644 index 0000000..8c52a75 --- /dev/null +++ b/Yi-6B-200K.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:274f397751646b9aa266a53a56121c4fce23b0f3e6f1b9345d77dcffd167473d +size 2709196640 diff --git a/Yi-6B-200K.Q4_K_M.gguf b/Yi-6B-200K.Q4_K_M.gguf new file mode 100644 index 0000000..648f10e --- /dev/null +++ b/Yi-6B-200K.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36079b6298ab4bbdfb5ba1f13aaeddc155bd498f9792c218de80894776a62980 +size 3673968480 diff --git a/Yi-6B-200K.Q4_K_S.gguf b/Yi-6B-200K.Q4_K_S.gguf new file mode 100644 index 0000000..b53b628 --- /dev/null +++ b/Yi-6B-200K.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:784e871dff6fa11ab7a27cb347210151bbed10bb622defab1cbc22e3b79f3162 +size 3502919520 diff --git a/Yi-6B-200K.Q5_K_M.gguf b/Yi-6B-200K.Q5_K_M.gguf new file mode 100644 index 0000000..c5d8d0f --- /dev/null +++ b/Yi-6B-200K.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aea1c9ca12d6d13ff7459a8c5e0a74070020b150c9c959d1249172a2f2d73d62 +size 4304424800 diff --git a/Yi-6B-200K.Q5_K_S.gguf b/Yi-6B-200K.Q5_K_S.gguf new file mode 100644 index 0000000..cfb9403 --- /dev/null +++ b/Yi-6B-200K.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3e6795bedb2ba3ea667f90459f6e1fe6600ad5f56789b4d415f11bf11545e37 +size 4204154720 diff --git a/Yi-6B-200K.Q6_K.gguf b/Yi-6B-200K.Q6_K.gguf new file mode 100644 index 0000000..19126b1 --- /dev/null +++ b/Yi-6B-200K.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c70dd092ef18f5f236d66f76c86e4f358246cb7225f9cee4625358875ee75ab +size 4974284640 diff --git a/Yi-6B-200K.Q8_0.gguf b/Yi-6B-200K.Q8_0.gguf new file mode 100644 index 0000000..4772e78 --- /dev/null +++ b/Yi-6B-200K.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:748e0277c2b1fb92d88041a348b6d8bee16df668d60c1417d74d899479727918 +size 6442127200 diff --git a/Yi-6B-200K.f16.gguf b/Yi-6B-200K.f16.gguf new file mode 100644 index 0000000..1e29ff3 --- /dev/null +++ b/Yi-6B-200K.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9900bd8f7345a4628666215e5f84d664b2287201807a79387d1190213ae044c +size 12124098400