commit 2912d968d32101e6810dd5f1ecec53163c65447a Author: ModelHub XC Date: Thu Jun 25 15:40:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KatipGPT-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c1651c4 --- /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 +KatipGPT-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KatipGPT-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KatipGPT-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KatipGPT-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KatipGPT-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KatipGPT-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KatipGPT-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KatipGPT-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +KatipGPT-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KatipGPT-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KatipGPT-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KatipGPT-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KatipGPT-Instruct.IQ4_XS.gguf b/KatipGPT-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..cf819d8 --- /dev/null +++ b/KatipGPT-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8976483f9b75cf40f959b60b9f8ab730023707801f02b7f92fa26715629fd0d9 +size 5223171840 diff --git a/KatipGPT-Instruct.Q2_K.gguf b/KatipGPT-Instruct.Q2_K.gguf new file mode 100644 index 0000000..ce125ea --- /dev/null +++ b/KatipGPT-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e43fd1bafe535d82bc8beac1bb87db5994399f87942e69ae5f22828b50cfa5f8 +size 3805398784 diff --git a/KatipGPT-Instruct.Q3_K_L.gguf b/KatipGPT-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..0ec3fdc --- /dev/null +++ b/KatipGPT-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8903284ec33066daf4aa9a5c599dbe37b61cafe97c05f18ff1d282a3cca1db74 +size 5132453632 diff --git a/KatipGPT-Instruct.Q3_K_M.gguf b/KatipGPT-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..e01df02 --- /dev/null +++ b/KatipGPT-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b665902ff7c1be29d1050c7de077dd1c1b41b6db21ab855cdb91fb999d412ea2 +size 4761782016 diff --git a/KatipGPT-Instruct.Q3_K_S.gguf b/KatipGPT-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..b63f8d4 --- /dev/null +++ b/KatipGPT-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b12860aee088bf68df3b78ea5f12a878f8b24168d212ddef9ff0664ca4f468 +size 4337665792 diff --git a/KatipGPT-Instruct.Q4_K_M.gguf b/KatipGPT-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..9ebb77b --- /dev/null +++ b/KatipGPT-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:600db5866501d092d97fe42b6db8f48a3f59f61e57997f449ce00c0ead17fc4b +size 5761058560 diff --git a/KatipGPT-Instruct.Q4_K_S.gguf b/KatipGPT-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..46ff6f0 --- /dev/null +++ b/KatipGPT-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cc6a14e36deccd6e53e5fbac167d7c887ee7801e463ff7c1182e3589cd6d344 +size 5478926080 diff --git a/KatipGPT-Instruct.Q5_K_M.gguf b/KatipGPT-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..244ca4a --- /dev/null +++ b/KatipGPT-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5efdac798f2ac582d2d6a116d6122912487b3820c2f84c7815e0f241385d997 +size 6647367424 diff --git a/KatipGPT-Instruct.Q5_K_S.gguf b/KatipGPT-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..629f7d0 --- /dev/null +++ b/KatipGPT-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367b114a5f333ec92188f8ead138014ab04b544b2320dc0626648d4eafe58ced +size 6483592960 diff --git a/KatipGPT-Instruct.Q6_K.gguf b/KatipGPT-Instruct.Q6_K.gguf new file mode 100644 index 0000000..b88799d --- /dev/null +++ b/KatipGPT-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee318d6bc7604e0d30293f3bac6008c1d5163fe1786c212aed1dbfa35dc10b09 +size 7589070592 diff --git a/KatipGPT-Instruct.Q8_0.gguf b/KatipGPT-Instruct.Q8_0.gguf new file mode 100644 index 0000000..94b0a97 --- /dev/null +++ b/KatipGPT-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:639d5b7dc54b47e74547d938e687e03f5a50d4056949c8eebe737ca02dbc38ab +size 9827149568 diff --git a/KatipGPT-Instruct.f16.gguf b/KatipGPT-Instruct.f16.gguf new file mode 100644 index 0000000..75d6fec --- /dev/null +++ b/KatipGPT-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f84a1429d07b0268da45e8a1430151a7bc24d2fee8758900c762f25853cf719a +size 18490681088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e8bd9e8 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: XyperAI/KatipGPT-Instruct +datasets: +- XyperAI/Ottoman-Dataset +language: +- en +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Ottoman +--- +## About + + + + + + + + + +static quants of https://huggingface.co/XyperAI/KatipGPT-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KatipGPT-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/KatipGPT-Instruct-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/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KatipGPT-Instruct-GGUF/resolve/main/KatipGPT-Instruct.f16.gguf) | f16 | 18.6 | 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. + +