commit 500cd08e3f1a68232ddb150430d94709d5c4e94a Author: ModelHub XC Date: Sat May 9 03:05:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/openchatgpt-neox-125m-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..35e98be --- /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 +openchatgpt-neox-125m.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +openchatgpt-neox-125m.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ba03057 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: mrsteyk/openchatgpt-neox-125m +language: +- en +library_name: transformers +license: +- creativeml-openrail-m +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- text generation +- pytorch +- casual-lm +--- +## About + + + + + + +static quants of https://huggingface.co/mrsteyk/openchatgpt-neox-125m + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#openchatgpt-neox-125m-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/openchatgpt-neox-125m-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/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/openchatgpt-neox-125m-GGUF/resolve/main/openchatgpt-neox-125m.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. + + diff --git a/openchatgpt-neox-125m.IQ4_XS.gguf b/openchatgpt-neox-125m.IQ4_XS.gguf new file mode 100644 index 0000000..268a873 --- /dev/null +++ b/openchatgpt-neox-125m.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11c030aa2ff2e8a03cd0af4762be41538af25cb50b43068e0ce5a5feab7f65a4 +size 99941408 diff --git a/openchatgpt-neox-125m.Q2_K.gguf b/openchatgpt-neox-125m.Q2_K.gguf new file mode 100644 index 0000000..4a7185e --- /dev/null +++ b/openchatgpt-neox-125m.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:383726027589d6c4aa3a644fe1df9f215d7804ec3fd1b830c36bebb645c98fd7 +size 78071296 diff --git a/openchatgpt-neox-125m.Q3_K_L.gguf b/openchatgpt-neox-125m.Q3_K_L.gguf new file mode 100644 index 0000000..6618cdb --- /dev/null +++ b/openchatgpt-neox-125m.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:089e77be37770f6b0a3bd1107c35e9c1b3b7e7e276df5faf8f10897a5368a971 +size 98968832 diff --git a/openchatgpt-neox-125m.Q3_K_M.gguf b/openchatgpt-neox-125m.Q3_K_M.gguf new file mode 100644 index 0000000..cb6aabb --- /dev/null +++ b/openchatgpt-neox-125m.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28fa167f4ecaf523cdf41f10f8f6ca62aefdc5a1e8639a87dc39802f873bff4d +size 94545152 diff --git a/openchatgpt-neox-125m.Q3_K_S.gguf b/openchatgpt-neox-125m.Q3_K_S.gguf new file mode 100644 index 0000000..ac4fb28 --- /dev/null +++ b/openchatgpt-neox-125m.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e77e2827c4853b14233d20e486c09a1c0d69d128839ae8d8294f9fcebaea5e +size 87024896 diff --git a/openchatgpt-neox-125m.Q4_K_M.gguf b/openchatgpt-neox-125m.Q4_K_M.gguf new file mode 100644 index 0000000..47be753 --- /dev/null +++ b/openchatgpt-neox-125m.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49787a04ccaa52c207cefcdce4d1a28a2f85eb02642b11dfc3300adbeb04ebb4 +size 109737376 diff --git a/openchatgpt-neox-125m.Q4_K_S.gguf b/openchatgpt-neox-125m.Q4_K_S.gguf new file mode 100644 index 0000000..a3bf002 --- /dev/null +++ b/openchatgpt-neox-125m.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb885f8f426bf0ed998d0b79a7cd0586fed09fbc66adbbaed93ee586fabb4cf6 +size 103728544 diff --git a/openchatgpt-neox-125m.Q5_K_M.gguf b/openchatgpt-neox-125m.Q5_K_M.gguf new file mode 100644 index 0000000..cc0c6e8 --- /dev/null +++ b/openchatgpt-neox-125m.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a0f72723a6e7d48678427971ead704149679c4658c64543d3ea25ca35caffe7 +size 123577312 diff --git a/openchatgpt-neox-125m.Q5_K_S.gguf b/openchatgpt-neox-125m.Q5_K_S.gguf new file mode 100644 index 0000000..b4b86f6 --- /dev/null +++ b/openchatgpt-neox-125m.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96415d3f38a54d6da3e511f6d73430692150fdb6776fc14f3c7536d82b1876fc +size 118877152 diff --git a/openchatgpt-neox-125m.Q6_K.gguf b/openchatgpt-neox-125m.Q6_K.gguf new file mode 100644 index 0000000..a6615b7 --- /dev/null +++ b/openchatgpt-neox-125m.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12488130b1f5f151baf245863dd736ee2a297221dc0e675c6b84d049ef35b998 +size 135285920 diff --git a/openchatgpt-neox-125m.Q8_0.gguf b/openchatgpt-neox-125m.Q8_0.gguf new file mode 100644 index 0000000..f8fabab --- /dev/null +++ b/openchatgpt-neox-125m.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88333a0385fe804bd9f4b9c28f9615441623ed4022e18f5840d53c88f9a7a492 +size 174559392 diff --git a/openchatgpt-neox-125m.f16.gguf b/openchatgpt-neox-125m.f16.gguf new file mode 100644 index 0000000..068f46f --- /dev/null +++ b/openchatgpt-neox-125m.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:829a17b9ad913f8644931ee4e9eecde29875db356b785d1829c8ed7474b8495b +size 326585952