commit 0fa5d3aa5e4bb046b9ae03153a63cf3a64a50280 Author: ModelHub XC Date: Sat Jun 13 22:52:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AI-Guru-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..01ca921 --- /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 +AI-Guru.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AI-Guru.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI-Guru.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI-Guru.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI-Guru.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AI-Guru.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AI-Guru.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AI-Guru.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI-Guru.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI-Guru.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI-Guru.f16.gguf filter=lfs diff=lfs merge=lfs -text +AI-Guru.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AI-Guru.IQ4_XS.gguf b/AI-Guru.IQ4_XS.gguf new file mode 100644 index 0000000..285d572 --- /dev/null +++ b/AI-Guru.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ad11e9b1df0a439888a8dba6b116edacac148a3500eaf1a78a2337f8111ee2 +size 3948667552 diff --git a/AI-Guru.Q2_K.gguf b/AI-Guru.Q2_K.gguf new file mode 100644 index 0000000..29e6e16 --- /dev/null +++ b/AI-Guru.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fefb645cab1f6830abaf4e708fca7bae602aa392c78c75b9bd74f1daf4f96918 +size 2722882208 diff --git a/AI-Guru.Q3_K_L.gguf b/AI-Guru.Q3_K_L.gguf new file mode 100644 index 0000000..231d4d3 --- /dev/null +++ b/AI-Guru.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:442e3a347d6d34c1f88ad4e1d2a746de5d46f67599b89b574725b3c657c6923b +size 3825984160 diff --git a/AI-Guru.Q3_K_M.gguf b/AI-Guru.Q3_K_M.gguf new file mode 100644 index 0000000..17fcd98 --- /dev/null +++ b/AI-Guru.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9c0e90e925e6a549a70b4cca4e4e364fa3c4bbd76b7b04c070ca351b5289136 +size 3522945696 diff --git a/AI-Guru.Q3_K_S.gguf b/AI-Guru.Q3_K_S.gguf new file mode 100644 index 0000000..3def6b7 --- /dev/null +++ b/AI-Guru.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315c1822f082beafc97e1a988ae14e1ab7f965e75e5b27af7012b726480d17d8 +size 3168527008 diff --git a/AI-Guru.Q4_K_M.gguf b/AI-Guru.Q4_K_M.gguf new file mode 100644 index 0000000..b3f5716 --- /dev/null +++ b/AI-Guru.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3486dff6cd151c3a6b0b93e8d7bfb5b184f9fad3bd4456bed3f0c23e8a49b9e2 +size 4372816544 diff --git a/AI-Guru.Q4_K_S.gguf b/AI-Guru.Q4_K_S.gguf new file mode 100644 index 0000000..3672d08 --- /dev/null +++ b/AI-Guru.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed4ef2424e5d02e8b8dda5de7ec43c9b859107b284adedddfc4bab08b6c56c12 +size 4144751264 diff --git a/AI-Guru.Q5_K_M.gguf b/AI-Guru.Q5_K_M.gguf new file mode 100644 index 0000000..9a616cd --- /dev/null +++ b/AI-Guru.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e044c3481161a0bda51755b95bc4c70eb4d302869658078f1bf0294b057f777d +size 5136179872 diff --git a/AI-Guru.Q5_K_S.gguf b/AI-Guru.Q5_K_S.gguf new file mode 100644 index 0000000..7f1abea --- /dev/null +++ b/AI-Guru.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a36ccd20e7521acc40c6377cf527f2c3162962d04d39a8748cc122d4f4bb174b +size 5002486432 diff --git a/AI-Guru.Q6_K.gguf b/AI-Guru.Q6_K.gguf new file mode 100644 index 0000000..712b5d1 --- /dev/null +++ b/AI-Guru.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b35d04303c48adb733b9e3b36c891d613292b82722e016e05b1f8d8524e5d18e +size 5947253408 diff --git a/AI-Guru.Q8_0.gguf b/AI-Guru.Q8_0.gguf new file mode 100644 index 0000000..313292d --- /dev/null +++ b/AI-Guru.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c693f215486fd9d4f0425341a62686951dccb2e30351bd813900e353b501f851 +size 7702569632 diff --git a/AI-Guru.f16.gguf b/AI-Guru.f16.gguf new file mode 100644 index 0000000..26fff89 --- /dev/null +++ b/AI-Guru.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ad42f0b2a8b364c2f52ea781961c5671e9491e96e07e0dcc200f5536f9db0e5 +size 14497342112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..16191ec --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: enzer1992/AI-Guru +language: +- si +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- fine-tuned +- GPT-2 +- Sinhala +- AI-Guru +--- +## About + + + + + + +static quants of https://huggingface.co/enzer1992/AI-Guru + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AI-Guru-GGUF).*** + +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/AI-Guru-GGUF/resolve/main/AI-Guru.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/AI-Guru-GGUF/resolve/main/AI-Guru.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/AI-Guru-GGUF/resolve/main/AI-Guru.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AI-Guru-GGUF/resolve/main/AI-Guru.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/AI-Guru-GGUF/resolve/main/AI-Guru.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/AI-Guru-GGUF/resolve/main/AI-Guru.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AI-Guru-GGUF/resolve/main/AI-Guru.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AI-Guru-GGUF/resolve/main/AI-Guru.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/AI-Guru-GGUF/resolve/main/AI-Guru.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/AI-Guru-GGUF/resolve/main/AI-Guru.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AI-Guru-GGUF/resolve/main/AI-Guru.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AI-Guru-GGUF/resolve/main/AI-Guru.f16.gguf) | f16 | 14.6 | 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. + +