commit fba0351b375eae1200a984011bbfda4797355c33 Author: ModelHub XC Date: Tue Sep 8 22:41:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GPT2-355M-from-scratch-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3dc8170 --- /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 +GPT2-355M-from-scratch.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-355M-from-scratch.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-355M-from-scratch.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-355M-from-scratch.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-355M-from-scratch.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-355M-from-scratch.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-355M-from-scratch.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-355M-from-scratch.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-355M-from-scratch.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-355M-from-scratch.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-355M-from-scratch.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-355M-from-scratch.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GPT2-355M-from-scratch.IQ4_XS.gguf b/GPT2-355M-from-scratch.IQ4_XS.gguf new file mode 100644 index 0000000..12200ef --- /dev/null +++ b/GPT2-355M-from-scratch.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827eeb8667fc3d49055c9046b695ed5c6c31fc286af5f1240684149b63ad66a4 +size 239218240 diff --git a/GPT2-355M-from-scratch.Q2_K.gguf b/GPT2-355M-from-scratch.Q2_K.gguf new file mode 100644 index 0000000..94fb14a --- /dev/null +++ b/GPT2-355M-from-scratch.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53c61befa140addb2ebb6f14de0f98a2b8cbf73c471900ed8efb0b1b1bfb29ed +size 185904256 diff --git a/GPT2-355M-from-scratch.Q3_K_L.gguf b/GPT2-355M-from-scratch.Q3_K_L.gguf new file mode 100644 index 0000000..4311b90 --- /dev/null +++ b/GPT2-355M-from-scratch.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75396762092ac9326d764c3ea737a8f65e9ed641b74bc91f8baa4b4357771569 +size 253259104 diff --git a/GPT2-355M-from-scratch.Q3_K_M.gguf b/GPT2-355M-from-scratch.Q3_K_M.gguf new file mode 100644 index 0000000..ce07e08 --- /dev/null +++ b/GPT2-355M-from-scratch.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a38616cb25276dce8e5bcd30972ef6815ce085e6d66a6794c7626cccc1ade6de +size 229404000 diff --git a/GPT2-355M-from-scratch.Q3_K_S.gguf b/GPT2-355M-from-scratch.Q3_K_S.gguf new file mode 100644 index 0000000..8ae8c64 --- /dev/null +++ b/GPT2-355M-from-scratch.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b224af7154177c796df219db99756b07a241cf0014fcc461eae06888bc115247 +size 201354592 diff --git a/GPT2-355M-from-scratch.Q4_K_M.gguf b/GPT2-355M-from-scratch.Q4_K_M.gguf new file mode 100644 index 0000000..2684a35 --- /dev/null +++ b/GPT2-355M-from-scratch.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584ed1922a76179d9689e7d0ed175798690d3a8725050428f6f6d6d04703f733 +size 271005792 diff --git a/GPT2-355M-from-scratch.Q4_K_S.gguf b/GPT2-355M-from-scratch.Q4_K_S.gguf new file mode 100644 index 0000000..6d16906 --- /dev/null +++ b/GPT2-355M-from-scratch.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae75b15044091cd17b2f593169989f7bf13721dcf7bd6d07595569dce3fb831d +size 251443296 diff --git a/GPT2-355M-from-scratch.Q5_K_M.gguf b/GPT2-355M-from-scratch.Q5_K_M.gguf new file mode 100644 index 0000000..435c153 --- /dev/null +++ b/GPT2-355M-from-scratch.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e465e25d15b8a60fa7de27ebc8ccd1fe7bcb4a373bae9c59d8a2aa896c840a36 +size 304177376 diff --git a/GPT2-355M-from-scratch.Q5_K_S.gguf b/GPT2-355M-from-scratch.Q5_K_S.gguf new file mode 100644 index 0000000..106f825 --- /dev/null +++ b/GPT2-355M-from-scratch.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79f7ca143d963b6284a3cf6a4abcf42817ebd85dd44986e3c6cc59686a87c555 +size 292479200 diff --git a/GPT2-355M-from-scratch.Q6_K.gguf b/GPT2-355M-from-scratch.Q6_K.gguf new file mode 100644 index 0000000..cd9cabc --- /dev/null +++ b/GPT2-355M-from-scratch.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecb816cdd26a78daf4c8efae68a70f6830842ed4cb66364718719a41ce47bbe4 +size 339422208 diff --git a/GPT2-355M-from-scratch.Q8_0.gguf b/GPT2-355M-from-scratch.Q8_0.gguf new file mode 100644 index 0000000..dd6034c --- /dev/null +++ b/GPT2-355M-from-scratch.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:065d276f5109887320a85a15acfd27c66b02feb0d64aaac3ff4d75a12f1dcd90 +size 437487808 diff --git a/GPT2-355M-from-scratch.f16.gguf b/GPT2-355M-from-scratch.f16.gguf new file mode 100644 index 0000000..491a240 --- /dev/null +++ b/GPT2-355M-from-scratch.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e44369359613aa5fac33e9407388571bee8e915221d1c396edf26eebb299bad +size 817096768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..33c8841 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: nachiketj14/GPT2-355M-from-scratch +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/nachiketj14/GPT2-355M-from-scratch + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GPT2-355M-from-scratch-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/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.Q4_K_S.gguf) | Q4_K_S | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.Q3_K_L.gguf) | Q3_K_L | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.Q4_K_M.gguf) | Q4_K_M | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2-355M-from-scratch-GGUF/resolve/main/GPT2-355M-from-scratch.f16.gguf) | f16 | 0.9 | 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. + +