commit 31e713eff7f1b7f6a62dc49b3a593f1e358039bb Author: ModelHub XC Date: Wed Jun 17 14:58:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/JAT-GPT2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9836aa1 --- /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 +JAT-GPT2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +JAT-GPT2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +JAT-GPT2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +JAT-GPT2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JAT-GPT2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JAT-GPT2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JAT-GPT2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JAT-GPT2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JAT-GPT2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JAT-GPT2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +JAT-GPT2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +JAT-GPT2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/JAT-GPT2.IQ4_XS.gguf b/JAT-GPT2.IQ4_XS.gguf new file mode 100644 index 0000000..20f31f3 --- /dev/null +++ b/JAT-GPT2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2af0859d4cf927327608cf9ac1ce6543d24dddf86294e0bd2690853f6ab9a42c +size 15962880 diff --git a/JAT-GPT2.Q2_K.gguf b/JAT-GPT2.Q2_K.gguf new file mode 100644 index 0000000..d429330 --- /dev/null +++ b/JAT-GPT2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d00d2d46c92c0018b61797a7f7d7c6aea919134f5e1e134763cd3fdc1a6e1d +size 15204096 diff --git a/JAT-GPT2.Q3_K_L.gguf b/JAT-GPT2.Q3_K_L.gguf new file mode 100644 index 0000000..c73d711 --- /dev/null +++ b/JAT-GPT2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586552bfc0c646137433ee126059d982ad34a30af517ff127c3b319772ca9697 +size 16147200 diff --git a/JAT-GPT2.Q3_K_M.gguf b/JAT-GPT2.Q3_K_M.gguf new file mode 100644 index 0000000..4b34a46 --- /dev/null +++ b/JAT-GPT2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f35806d6e79d21e87c1b2cbc2544d7346c888979f18b20f2943ae31fef36b273 +size 15901440 diff --git a/JAT-GPT2.Q3_K_S.gguf b/JAT-GPT2.Q3_K_S.gguf new file mode 100644 index 0000000..6af74fd --- /dev/null +++ b/JAT-GPT2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a4277841161d2b56fdca1b41a08f09ecaa9081004bb6dd97a099b753bfcccb1 +size 15483648 diff --git a/JAT-GPT2.Q4_K_M.gguf b/JAT-GPT2.Q4_K_M.gguf new file mode 100644 index 0000000..b18c494 --- /dev/null +++ b/JAT-GPT2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ea11a371b8a69a6c66b861211155a8ee2971527dd957b52e44b9cee7d703ddb +size 16392960 diff --git a/JAT-GPT2.Q4_K_S.gguf b/JAT-GPT2.Q4_K_S.gguf new file mode 100644 index 0000000..be53d14 --- /dev/null +++ b/JAT-GPT2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de3f0f5f4491acdd6c9afc1ef7d69f018b011aef63d1140240d7c507c1c8df7a +size 16110336 diff --git a/JAT-GPT2.Q5_K_M.gguf b/JAT-GPT2.Q5_K_M.gguf new file mode 100644 index 0000000..8f7be74 --- /dev/null +++ b/JAT-GPT2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c233d1a46f70dce51d5ede90d7970213aba9a14aa9199b855df2be34b8a2169 +size 16926464 diff --git a/JAT-GPT2.Q5_K_S.gguf b/JAT-GPT2.Q5_K_S.gguf new file mode 100644 index 0000000..922161a --- /dev/null +++ b/JAT-GPT2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a49ad73b97cd95ddfa9a358a25eb7340fcef19ad6ddee804a0233830ef3606c +size 16700160 diff --git a/JAT-GPT2.Q6_K.gguf b/JAT-GPT2.Q6_K.gguf new file mode 100644 index 0000000..d21b87c --- /dev/null +++ b/JAT-GPT2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5285d60dddff15fb84ab11fe257e1dcf7b3ef6fe6ed0cb7b6f7c74a173b5018 +size 17326848 diff --git a/JAT-GPT2.Q8_0.gguf b/JAT-GPT2.Q8_0.gguf new file mode 100644 index 0000000..0d02676 --- /dev/null +++ b/JAT-GPT2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b08e1dfac11e0d134f56e21f044bb38945b49e44957ab167785f0e1861fa69 +size 21585568 diff --git a/JAT-GPT2.f16.gguf b/JAT-GPT2.f16.gguf new file mode 100644 index 0000000..72c59d5 --- /dev/null +++ b/JAT-GPT2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f29692af6bdfc21f54334d098d7a67363cbf1757659294f20631070dc14c8680 +size 38070912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..02c9b4c --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: itsme-nishanth/JAT-GPT2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/itsme-nishanth/JAT-GPT2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#JAT-GPT2-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/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.Q2_K.gguf) | Q2_K | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.Q3_K_S.gguf) | Q3_K_S | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.Q3_K_M.gguf) | Q3_K_M | 0.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.IQ4_XS.gguf) | IQ4_XS | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.Q4_K_S.gguf) | Q4_K_S | 0.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.Q3_K_L.gguf) | Q3_K_L | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.Q4_K_M.gguf) | Q4_K_M | 0.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.Q5_K_S.gguf) | Q5_K_S | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.Q5_K_M.gguf) | Q5_K_M | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.Q6_K.gguf) | Q6_K | 0.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.Q8_0.gguf) | Q8_0 | 0.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/JAT-GPT2-GGUF/resolve/main/JAT-GPT2.f16.gguf) | f16 | 0.1 | 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. + +