commit 8e27493e403327375272d403f7660dd99b8fec0e Author: ModelHub XC Date: Mon Jun 1 21:20:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GPT2-137M-Chat-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b04f060 --- /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 +GPT2-137M-Chat-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-137M-Chat-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-137M-Chat-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-137M-Chat-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-137M-Chat-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-137M-Chat-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-137M-Chat-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-137M-Chat-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-137M-Chat-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-137M-Chat-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-137M-Chat-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GPT2-137M-Chat-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GPT2-137M-Chat-v1.0.IQ4_XS.gguf b/GPT2-137M-Chat-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..d414250 --- /dev/null +++ b/GPT2-137M-Chat-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68656a9173c1367c1211058b0fa6d2ce75006ed7c487788527227c4be1e583b6 +size 82558944 diff --git a/GPT2-137M-Chat-v1.0.Q2_K.gguf b/GPT2-137M-Chat-v1.0.Q2_K.gguf new file mode 100644 index 0000000..b6f6a70 --- /dev/null +++ b/GPT2-137M-Chat-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d277ec1212e4e861a114a2eb70b96cc135653fc9030b7cfbdb8879750f877551 +size 68532192 diff --git a/GPT2-137M-Chat-v1.0.Q3_K_L.gguf b/GPT2-137M-Chat-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..59efa5b --- /dev/null +++ b/GPT2-137M-Chat-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93313bd955adab900e501b71f25eb94fe7404f50d8712b19a9abece55ac28909 +size 85508064 diff --git a/GPT2-137M-Chat-v1.0.Q3_K_M.gguf b/GPT2-137M-Chat-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..e6398b5 --- /dev/null +++ b/GPT2-137M-Chat-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0d6dae94ac751901307781346b790df6f39b83c0ace1707fd0e5164b52a65c2 +size 81084384 diff --git a/GPT2-137M-Chat-v1.0.Q3_K_S.gguf b/GPT2-137M-Chat-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..8452a48 --- /dev/null +++ b/GPT2-137M-Chat-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d4a1698204c59c7dcf692e51a36962846b9648b7aa9fc8b70e6b1e83755a13 +size 73564128 diff --git a/GPT2-137M-Chat-v1.0.Q4_K_M.gguf b/GPT2-137M-Chat-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..5254dfe --- /dev/null +++ b/GPT2-137M-Chat-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfbbf902609c04919e0af4bc939cf10c454d815313eb5c6b2a74efa4f0c22070 +size 91148256 diff --git a/GPT2-137M-Chat-v1.0.Q4_K_S.gguf b/GPT2-137M-Chat-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..6fb8f02 --- /dev/null +++ b/GPT2-137M-Chat-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:467adfb7c50bc7f4db696dcc34712081275cc6ef8b2d70c48d7e22ecb9d8109f +size 85139424 diff --git a/GPT2-137M-Chat-v1.0.Q5_K_M.gguf b/GPT2-137M-Chat-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..e857f8d --- /dev/null +++ b/GPT2-137M-Chat-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb3847a3938ac4f5c70cf65c073cd5ce03cbb82010a1067e47fd3eb2fde4f60b +size 100161504 diff --git a/GPT2-137M-Chat-v1.0.Q5_K_S.gguf b/GPT2-137M-Chat-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..7ae1069 --- /dev/null +++ b/GPT2-137M-Chat-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d065ef68bd1e5b3052c9ac538a7cb0d93c5e63fa51ad1e05075f999177af82 +size 95461344 diff --git a/GPT2-137M-Chat-v1.0.Q6_K.gguf b/GPT2-137M-Chat-v1.0.Q6_K.gguf new file mode 100644 index 0000000..0bd5113 --- /dev/null +++ b/GPT2-137M-Chat-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38fa0168294cbd7458aa300b88b6e3f70ad712b1f4f2386ad837fae5dee12411 +size 106741728 diff --git a/GPT2-137M-Chat-v1.0.Q8_0.gguf b/GPT2-137M-Chat-v1.0.Q8_0.gguf new file mode 100644 index 0000000..c4ce4f2 --- /dev/null +++ b/GPT2-137M-Chat-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b5aeaf70e478a7c9aeb35bcc9e75b1d57b2ee7c09c4c61bc8d5e70a58f2cab +size 136659648 diff --git a/GPT2-137M-Chat-v1.0.f16.gguf b/GPT2-137M-Chat-v1.0.f16.gguf new file mode 100644 index 0000000..fa6ba4d --- /dev/null +++ b/GPT2-137M-Chat-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5d68168328ab8ab0c498e09d8d74ebed98687ed581158f2014dc1005bde47b4 +size 252470912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bbd1894 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: NuclearAi/GPT2-137M-Chat-v1.0 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/NuclearAi/GPT2-137M-Chat-v1.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GPT2-137M-Chat-v1.0-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/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2-137M-Chat-v1.0-GGUF/resolve/main/GPT2-137M-Chat-v1.0.f16.gguf) | f16 | 0.4 | 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. + +