commit ca9557f2040e9738db6b894b96f02f8556d275eb Author: ModelHub XC Date: Sat May 9 12:25:52 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/alex_gpt3_Doctextfull-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c88390b --- /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 +alex_gpt3_Doctextfull.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +alex_gpt3_Doctextfull.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +alex_gpt3_Doctextfull.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +alex_gpt3_Doctextfull.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +alex_gpt3_Doctextfull.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +alex_gpt3_Doctextfull.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +alex_gpt3_Doctextfull.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +alex_gpt3_Doctextfull.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +alex_gpt3_Doctextfull.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +alex_gpt3_Doctextfull.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +alex_gpt3_Doctextfull.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +alex_gpt3_Doctextfull.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..36fc03f --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: danurahul/alex_gpt3_Doctextfull +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/danurahul/alex_gpt3_Doctextfull + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-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/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/alex_gpt3_Doctextfull-GGUF/resolve/main/alex_gpt3_Doctextfull.f16.gguf) | f16 | 0.3 | 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/alex_gpt3_Doctextfull.IQ4_XS.gguf b/alex_gpt3_Doctextfull.IQ4_XS.gguf new file mode 100644 index 0000000..b89eac1 --- /dev/null +++ b/alex_gpt3_Doctextfull.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165942ed17471a9340ad0c6f75d96c65ad9b6a741b6bbc1ddf93025d243c2f47 +size 59385760 diff --git a/alex_gpt3_Doctextfull.Q2_K.gguf b/alex_gpt3_Doctextfull.Q2_K.gguf new file mode 100644 index 0000000..33fa0bf --- /dev/null +++ b/alex_gpt3_Doctextfull.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1427ac344ec3950f7077933ee30a41924b77c7535a1ec91613ea07004dbfc3e +size 52556704 diff --git a/alex_gpt3_Doctextfull.Q3_K_L.gguf b/alex_gpt3_Doctextfull.Q3_K_L.gguf new file mode 100644 index 0000000..73d3673 --- /dev/null +++ b/alex_gpt3_Doctextfull.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aec25ffe4a0cafeb45458ea3925cdb8380a89dd9d6a855ae38db33b72b3fe686 +size 61044640 diff --git a/alex_gpt3_Doctextfull.Q3_K_M.gguf b/alex_gpt3_Doctextfull.Q3_K_M.gguf new file mode 100644 index 0000000..8a11d1e --- /dev/null +++ b/alex_gpt3_Doctextfull.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9374be59cef58ae34184da6bc9e9be8fabad5c02e1d1eee142d6ec22f836a4b1 +size 58832800 diff --git a/alex_gpt3_Doctextfull.Q3_K_S.gguf b/alex_gpt3_Doctextfull.Q3_K_S.gguf new file mode 100644 index 0000000..abe5b7e --- /dev/null +++ b/alex_gpt3_Doctextfull.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4ba39435cc6e458342f144756fa58148f599ec8fcc89f2d12810e00f715727 +size 55072672 diff --git a/alex_gpt3_Doctextfull.Q4_K_M.gguf b/alex_gpt3_Doctextfull.Q4_K_M.gguf new file mode 100644 index 0000000..768be6a --- /dev/null +++ b/alex_gpt3_Doctextfull.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e4b1a1c9aecaa3b947131c3b0bc48b4bbce871de3f8fd2fa36ca9b9a777adf +size 63256480 diff --git a/alex_gpt3_Doctextfull.Q4_K_S.gguf b/alex_gpt3_Doctextfull.Q4_K_S.gguf new file mode 100644 index 0000000..5b5a39a --- /dev/null +++ b/alex_gpt3_Doctextfull.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f80504bbd25ebc24f7a1d946254da0cbd50a9c187834d55d9f7f8cb8d5230067 +size 60712864 diff --git a/alex_gpt3_Doctextfull.Q5_K_M.gguf b/alex_gpt3_Doctextfull.Q5_K_M.gguf new file mode 100644 index 0000000..7c20f52 --- /dev/null +++ b/alex_gpt3_Doctextfull.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc78a326d9a1a1422c407d0ed4c5ceeabfeb7b613e14437b0a5accd0daf2109a +size 68058016 diff --git a/alex_gpt3_Doctextfull.Q5_K_S.gguf b/alex_gpt3_Doctextfull.Q5_K_S.gguf new file mode 100644 index 0000000..5d77161 --- /dev/null +++ b/alex_gpt3_Doctextfull.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8f57e545a49096c3ac213c17f799fc93db51a0e95512dd04b30e4239bd9507e +size 66021280 diff --git a/alex_gpt3_Doctextfull.Q6_K.gguf b/alex_gpt3_Doctextfull.Q6_K.gguf new file mode 100644 index 0000000..404f29d --- /dev/null +++ b/alex_gpt3_Doctextfull.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f078e0277523ccc4a64375acecababfbd9a1c1ccf25d63d79053330cbd05cdbd +size 71661472 diff --git a/alex_gpt3_Doctextfull.Q8_0.gguf b/alex_gpt3_Doctextfull.Q8_0.gguf new file mode 100644 index 0000000..d221f0b --- /dev/null +++ b/alex_gpt3_Doctextfull.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:448d69e562f90083ad4029dc4b296a2254d5f73bea247430a5549179fd77d061 +size 91294336 diff --git a/alex_gpt3_Doctextfull.f16.gguf b/alex_gpt3_Doctextfull.f16.gguf new file mode 100644 index 0000000..fda6f53 --- /dev/null +++ b/alex_gpt3_Doctextfull.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c1675be7c505d075e11df0724d11100caef552a6cd7e2b5841869411ae978d7 +size 167292480