commit 1a7de4b054a369bc5c7fde70f45aa7780584b6ad Author: ModelHub XC Date: Thu Sep 24 10:05:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gpt2-insight-v1.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e40c7ec --- /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-insight-v1.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt2-insight-v1.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt2-insight-v1.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gpt2-insight-v1.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt2-insight-v1.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt2-insight-v1.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt2-insight-v1.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt2-insight-v1.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt2-insight-v1.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt2-insight-v1.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt2-insight-v1.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gpt2-insight-v1.2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d2aec23 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: migueldeguzmandev/gpt2-insight-v1.2 +language: +- en +library_name: transformers +license: bigscience-openrail-m +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/migueldeguzmandev/gpt2-insight-v1.2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gpt2-insight-v1.2-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-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.Q2_K.gguf) | Q2_K | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/gpt2-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/gpt2-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/gpt2-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gpt2-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/gpt2-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gpt2-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gpt2-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/gpt2-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.Q5_K_M.gguf) | Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/gpt2-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gpt2-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.Q8_0.gguf) | Q8_0 | 1.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gpt2-insight-v1.2-GGUF/resolve/main/gpt2-insight-v1.2.f16.gguf) | f16 | 3.4 | 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/gpt2-insight-v1.2.IQ4_XS.gguf b/gpt2-insight-v1.2.IQ4_XS.gguf new file mode 100644 index 0000000..20af9ff --- /dev/null +++ b/gpt2-insight-v1.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1787195756750bf1138240ad353b43d88ac4ab97001859d96683584d80becde +size 966708256 diff --git a/gpt2-insight-v1.2.Q2_K.gguf b/gpt2-insight-v1.2.Q2_K.gguf new file mode 100644 index 0000000..d7035fe --- /dev/null +++ b/gpt2-insight-v1.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd39bbcc2c8779c721d069cf5206d682d3a62b1d4135a0549a8c1aeec8de8787 +size 907188256 diff --git a/gpt2-insight-v1.2.Q3_K_L.gguf b/gpt2-insight-v1.2.Q3_K_L.gguf new file mode 100644 index 0000000..4b9be2f --- /dev/null +++ b/gpt2-insight-v1.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80692650bafee84fc74fba295c97b80eda804b6b3b3764f295fd6bd92ba40143 +size 1103028256 diff --git a/gpt2-insight-v1.2.Q3_K_M.gguf b/gpt2-insight-v1.2.Q3_K_M.gguf new file mode 100644 index 0000000..eaf3d9c --- /dev/null +++ b/gpt2-insight-v1.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec2aa308119cdb734e8530598c26a44eb91c3341f19a051affc929bee879953 +size 1037748256 diff --git a/gpt2-insight-v1.2.Q3_K_S.gguf b/gpt2-insight-v1.2.Q3_K_S.gguf new file mode 100644 index 0000000..7269834 --- /dev/null +++ b/gpt2-insight-v1.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5afd6d9e78e044e8e3404f28c03498a03ec4812799e6b99d530cc27150f58484 +size 907188256 diff --git a/gpt2-insight-v1.2.Q4_K_M.gguf b/gpt2-insight-v1.2.Q4_K_M.gguf new file mode 100644 index 0000000..80417ff --- /dev/null +++ b/gpt2-insight-v1.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e43bb55363872180e13c700607ad4d5e2874df4eca417ab89af58b3691c1103e +size 1191799648 diff --git a/gpt2-insight-v1.2.Q4_K_S.gguf b/gpt2-insight-v1.2.Q4_K_S.gguf new file mode 100644 index 0000000..dcd9a7f --- /dev/null +++ b/gpt2-insight-v1.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e169c4c49f41620f1774f855ba847aa6ff6792c1d19624b436a337e534226f3 +size 1113079648 diff --git a/gpt2-insight-v1.2.Q5_K_M.gguf b/gpt2-insight-v1.2.Q5_K_M.gguf new file mode 100644 index 0000000..333b915 --- /dev/null +++ b/gpt2-insight-v1.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf9ebce51974246e24d749bba67432ba64f316ce679b1889a69d133e79c09bda +size 1381145344 diff --git a/gpt2-insight-v1.2.Q5_K_S.gguf b/gpt2-insight-v1.2.Q5_K_S.gguf new file mode 100644 index 0000000..57a8188 --- /dev/null +++ b/gpt2-insight-v1.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:325f204fa73c9bf4e6ea37f43ab473931e1321631b2ae7c9dd4641539c30c18e +size 1233305344 diff --git a/gpt2-insight-v1.2.Q6_K.gguf b/gpt2-insight-v1.2.Q6_K.gguf new file mode 100644 index 0000000..bd66379 --- /dev/null +++ b/gpt2-insight-v1.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70d8f33935e42d28536f9f5766212c8158855f4198a21a5dd50bef1d72dd2253 +size 1630913856 diff --git a/gpt2-insight-v1.2.Q8_0.gguf b/gpt2-insight-v1.2.Q8_0.gguf new file mode 100644 index 0000000..e6fd63a --- /dev/null +++ b/gpt2-insight-v1.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df56a86b45dc10045c1c592622ab400fefa823babeeccef4d0b67abe95163e80 +size 1749953856 diff --git a/gpt2-insight-v1.2.f16.gguf b/gpt2-insight-v1.2.f16.gguf new file mode 100644 index 0000000..c9fb9ac --- /dev/null +++ b/gpt2-insight-v1.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bb1c7e8efbd94b421594d2fae10ddfc2e795f8e284755d8d2658eb1fa10b5c1 +size 3283124800