commit 6ae9c8d8b67bd75aa0a14b2b9a977235645d62ed Author: ModelHub XC Date: Wed Apr 22 00:56:42 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/kurage-en-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cdb85e4 --- /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 +kurage-en.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kurage-en.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +kurage-en.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kurage-en.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kurage-en.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +kurage-en.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +kurage-en.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +kurage-en.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kurage-en.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kurage-en.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kurage-en.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +kurage-en.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..92f2df4 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: lightblue/kurage-en +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- RAG +--- +## About + + + + + + +static quants of https://huggingface.co/lightblue/kurage-en + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/kurage-en-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/kurage-en-GGUF/resolve/main/kurage-en.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/kurage-en-GGUF/resolve/main/kurage-en.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/kurage-en.IQ4_XS.gguf b/kurage-en.IQ4_XS.gguf new file mode 100644 index 0000000..242bc7b --- /dev/null +++ b/kurage-en.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:628f127afe6035935ab87b7ae2635e312b53f9e7b4ba28e0cb4a4ba16f0d498e +size 4248271840 diff --git a/kurage-en.Q2_K.gguf b/kurage-en.Q2_K.gguf new file mode 100644 index 0000000..b3cdfa1 --- /dev/null +++ b/kurage-en.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a197b0e4de7b71bbe4b8dee31e393a3d00606dae8b52c15a5c60e2e568b4bff +size 3014216416 diff --git a/kurage-en.Q3_K_L.gguf b/kurage-en.Q3_K_L.gguf new file mode 100644 index 0000000..5ca295d --- /dev/null +++ b/kurage-en.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3206d0a3cb5531bf22f4410b3566e8de678f449bc00faab986584ddc18d54325 +size 4086584160 diff --git a/kurage-en.Q3_K_M.gguf b/kurage-en.Q3_K_M.gguf new file mode 100644 index 0000000..507c9c0 --- /dev/null +++ b/kurage-en.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39c9dbb9671f954a885ce81ad61b53aabd8eff46b987f1cd3c1d300ffd343b24 +size 3806516064 diff --git a/kurage-en.Q3_K_S.gguf b/kurage-en.Q3_K_S.gguf new file mode 100644 index 0000000..34e71c7 --- /dev/null +++ b/kurage-en.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a3408dc058a0a67e85984085d1603ab372ebc4053b13917d081acf229cdf75c +size 3490493280 diff --git a/kurage-en.Q4_0_4_4.gguf b/kurage-en.Q4_0_4_4.gguf new file mode 100644 index 0000000..74be95c --- /dev/null +++ b/kurage-en.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d499477401593949084468f39408d67764e2be1e3e4c3e7e729287b1bd2f100 +size 4429317600 diff --git a/kurage-en.Q4_K_M.gguf b/kurage-en.Q4_K_M.gguf new file mode 100644 index 0000000..3047ea6 --- /dev/null +++ b/kurage-en.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a0e3bfe3340bd5ab80757b03e48d87752a3f69f5a6688c58fca15bf1486f7ac +size 4681000416 diff --git a/kurage-en.Q4_K_S.gguf b/kurage-en.Q4_K_S.gguf new file mode 100644 index 0000000..2c38c9e --- /dev/null +++ b/kurage-en.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4660720ce1a0ecef02c3abaea45f6250fc97ccdfeb844409a57c9b9bf511959a +size 4455695840 diff --git a/kurage-en.Q5_K_M.gguf b/kurage-en.Q5_K_M.gguf new file mode 100644 index 0000000..30923c5 --- /dev/null +++ b/kurage-en.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d9f01874f5d687ca41fbcc1eb444718096413988745e9e19bd5e59f5722d93 +size 5442571744 diff --git a/kurage-en.Q5_K_S.gguf b/kurage-en.Q5_K_S.gguf new file mode 100644 index 0000000..c624906 --- /dev/null +++ b/kurage-en.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a62872d75d3c5a936c5500e2a74bd3b331ec4a6c6c0a98ae1370f140118b060d +size 5312916960 diff --git a/kurage-en.Q6_K.gguf b/kurage-en.Q6_K.gguf new file mode 100644 index 0000000..9fdf455 --- /dev/null +++ b/kurage-en.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d63c907443b0e3cef87d528a60278c5d31c5e07e8f6a41321286336febf6ab +size 6251741280 diff --git a/kurage-en.Q8_0.gguf b/kurage-en.Q8_0.gguf new file mode 100644 index 0000000..f0e4c28 --- /dev/null +++ b/kurage-en.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7093ec39367de6f5ba69e3e66c9cc2b7a7f3fab5211c4ffd9358aa4b032753a7 +size 8095345504 diff --git a/kurage-en.f16.gguf b/kurage-en.f16.gguf new file mode 100644 index 0000000..d41088e --- /dev/null +++ b/kurage-en.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4419ec57be624d0ba96db74513f9caf44fb9c8001612c54e993e8185985278d +size 15231877984