commit b15c03ddd5786549183ff6382abc57cf9f27d3f9 Author: ModelHub XC Date: Thu Jun 11 14:26:18 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Yi-6B-200K-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..86a0ba6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..959d570 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: 01-ai/Yi-6B-200K +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/01-ai/Yi-6B-200K + + +static quants are available at https://huggingface.co/mradermacher/Yi-6B-200K-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-i1-GGUF/resolve/main/Yi-6B-200K.i1-IQ1_S.gguf) | i1-IQ1_S | 1.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-IQ1_M.gguf) | i1-IQ1_M | 1.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-IQ2_S.gguf) | i1-IQ2_S | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-IQ2_M.gguf) | i1-IQ2_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-Q2_K.gguf) | i1-Q2_K | 2.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-IQ3_S.gguf) | i1-IQ3_S | 2.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-IQ3_M.gguf) | i1-IQ3_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-Q4_0.gguf) | i1-Q4_0 | 3.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-Q4_K_S.gguf) | i1-Q4_K_S | 3.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-Q4_K_M.gguf) | i1-Q4_K_M | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-Q5_K_M.gguf) | i1-Q5_K_M | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-i1-GGUF/resolve/main/Yi-6B-200K.i1-Q6_K.gguf) | i1-Q6_K | 5.1 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/Yi-6B-200K.i1-IQ1_M.gguf b/Yi-6B-200K.i1-IQ1_M.gguf new file mode 100644 index 0000000..ee4ade7 --- /dev/null +++ b/Yi-6B-200K.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f30986f22141436ce5a4cef8052f57122c9d454e722100b2f0f46fae2b8c84d9 +size 1543671872 diff --git a/Yi-6B-200K.i1-IQ1_S.gguf b/Yi-6B-200K.i1-IQ1_S.gguf new file mode 100644 index 0000000..d0ab1d8 --- /dev/null +++ b/Yi-6B-200K.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f30390674849f4b1784b7dc649823e781ae50bcc960b27abcad14378ea279eb +size 1432293440 diff --git a/Yi-6B-200K.i1-IQ2_M.gguf b/Yi-6B-200K.i1-IQ2_M.gguf new file mode 100644 index 0000000..68a1660 --- /dev/null +++ b/Yi-6B-200K.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b33d986f25aa58dfa5804ddfb6fa0db50c5c63887bd4fd224aac7542277d65ee +size 2163527744 diff --git a/Yi-6B-200K.i1-IQ2_S.gguf b/Yi-6B-200K.i1-IQ2_S.gguf new file mode 100644 index 0000000..9b20651 --- /dev/null +++ b/Yi-6B-200K.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf0f11d58f364060006b14a515c7c3e052f22e45abc2ffa7dff17037926a475 +size 2015023168 diff --git a/Yi-6B-200K.i1-IQ2_XS.gguf b/Yi-6B-200K.i1-IQ2_XS.gguf new file mode 100644 index 0000000..6e12edd --- /dev/null +++ b/Yi-6B-200K.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bbca596a59a938fc9c3fe2a4ae6f3d82ca7282a73b65cdf50b82f1ccdd56f8c +size 1894584384 diff --git a/Yi-6B-200K.i1-IQ2_XXS.gguf b/Yi-6B-200K.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..6daa705 --- /dev/null +++ b/Yi-6B-200K.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e60c4a70d19d2af69ba99fda0b4b9a50ed3cde5b95f7886e2a036176394f1408 +size 1729302592 diff --git a/Yi-6B-200K.i1-IQ3_M.gguf b/Yi-6B-200K.i1-IQ3_M.gguf new file mode 100644 index 0000000..fb18ce0 --- /dev/null +++ b/Yi-6B-200K.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c3b054a3c73cb42ffe501ef8cee90e8d22ab6d4b813d2b07041f645b2710718 +size 2813366336 diff --git a/Yi-6B-200K.i1-IQ3_S.gguf b/Yi-6B-200K.i1-IQ3_S.gguf new file mode 100644 index 0000000..7a61f0e --- /dev/null +++ b/Yi-6B-200K.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f99df43cd85f74421eb8a037e2648a8f429a314a997b2cabf745043156ee81b +size 2718109760 diff --git a/Yi-6B-200K.i1-IQ3_XS.gguf b/Yi-6B-200K.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8ee8143 --- /dev/null +++ b/Yi-6B-200K.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d5a170b689cc65945ab0c87e4db290fcdcfb5798d6afbb16adf81f5dcc07c87 +size 2588348480 diff --git a/Yi-6B-200K.i1-IQ3_XXS.gguf b/Yi-6B-200K.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ae880aa --- /dev/null +++ b/Yi-6B-200K.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a88c5b2e0724694e919e9bc9dc4c9673940a386bf85a09ebe0015088bb557943 +size 2414334016 diff --git a/Yi-6B-200K.i1-IQ4_XS.gguf b/Yi-6B-200K.i1-IQ4_XS.gguf new file mode 100644 index 0000000..a879ce7 --- /dev/null +++ b/Yi-6B-200K.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:515361e0a9dec0aba5629cde221bda0fa6a8722604bf181cc77316871336a04d +size 3308605504 diff --git a/Yi-6B-200K.i1-Q2_K.gguf b/Yi-6B-200K.i1-Q2_K.gguf new file mode 100644 index 0000000..1f16ea8 --- /dev/null +++ b/Yi-6B-200K.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab4890cced1818ba6fd912d45de255ee49af9a3395cea4cd4da06d70f4f34778 +size 2337067072 diff --git a/Yi-6B-200K.i1-Q2_K_S.gguf b/Yi-6B-200K.i1-Q2_K_S.gguf new file mode 100644 index 0000000..17748c7 --- /dev/null +++ b/Yi-6B-200K.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7031b162b0cf01139429bdb7bbd76a2ea9ffcec1dfffeb26376b813dd0071f7 +size 2178273600 diff --git a/Yi-6B-200K.i1-Q3_K_L.gguf b/Yi-6B-200K.i1-Q3_K_L.gguf new file mode 100644 index 0000000..540a427 --- /dev/null +++ b/Yi-6B-200K.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:242dc79642abcb67a57483f0db6b3ab553380c159c11b3f0c56b7fbe1172b52b +size 3236892736 diff --git a/Yi-6B-200K.i1-Q3_K_M.gguf b/Yi-6B-200K.i1-Q3_K_M.gguf new file mode 100644 index 0000000..19ee051 --- /dev/null +++ b/Yi-6B-200K.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4bf69c4ab7fc63a13a8a4234855c07790cc65b1d742a868ba1b93dcbaf927d +size 2992836672 diff --git a/Yi-6B-200K.i1-Q3_K_S.gguf b/Yi-6B-200K.i1-Q3_K_S.gguf new file mode 100644 index 0000000..66efe3e --- /dev/null +++ b/Yi-6B-200K.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0f2bdeda73d2374ceb9c58a9a1bd7fba7133f16349dcfa81491b8c096f1161f +size 2709196864 diff --git a/Yi-6B-200K.i1-Q4_0.gguf b/Yi-6B-200K.i1-Q4_0.gguf new file mode 100644 index 0000000..5baa4f2 --- /dev/null +++ b/Yi-6B-200K.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a0d7318af0751b4caa585dea39ebff1715c6b7fd9908a8175ea92f09f544372 +size 3490598976 diff --git a/Yi-6B-200K.i1-Q4_K_M.gguf b/Yi-6B-200K.i1-Q4_K_M.gguf new file mode 100644 index 0000000..088ab2c --- /dev/null +++ b/Yi-6B-200K.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3439625d2e91dfa00049b0b1480b0fd8b0ce6194f42ce762ea2afa1cb1520844 +size 3673968704 diff --git a/Yi-6B-200K.i1-Q4_K_S.gguf b/Yi-6B-200K.i1-Q4_K_S.gguf new file mode 100644 index 0000000..a1c8c40 --- /dev/null +++ b/Yi-6B-200K.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe41e83fa339c932c434a330f397c67fdf5a5cc9bdf69557b5e72f9806d9a950 +size 3502919744 diff --git a/Yi-6B-200K.i1-Q5_K_M.gguf b/Yi-6B-200K.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7278ab3 --- /dev/null +++ b/Yi-6B-200K.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11c752abc94b22c7f1a14b37728eb8caeea265b67e05dd41d5befdca2c18d522 +size 4304425024 diff --git a/Yi-6B-200K.i1-Q5_K_S.gguf b/Yi-6B-200K.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e9333ae --- /dev/null +++ b/Yi-6B-200K.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2caf7bb0e185823fcfee1f80ae2b34e582c85cdd57017b4cd2d05ccb9dd16290 +size 4204154944 diff --git a/Yi-6B-200K.i1-Q6_K.gguf b/Yi-6B-200K.i1-Q6_K.gguf new file mode 100644 index 0000000..ccbaada --- /dev/null +++ b/Yi-6B-200K.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:428ccd5241cdb116327ebef5cc249835985594d9952eb7717ef538c79c131eb8 +size 4974284864 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..410da21 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d90a3b95f3748a2fb11fac129c9bfe5e873e3ca5d449d538d130271d4a1e733a +size 4562177