commit ed9717f1409b42f88aefeec2e32cdaa75bd04b83 Author: ModelHub XC Date: Mon Oct 5 16:05:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Codex-24B-Small-3.2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /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 +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Codex-24B-Small-3.2.i1-IQ2_XS.gguf b/Codex-24B-Small-3.2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..5bd7776 --- /dev/null +++ b/Codex-24B-Small-3.2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466fa1bf660a8ffd2826543d55810aadb39124764a812a898898b7d6ede5516f +size 7207032544 diff --git a/Codex-24B-Small-3.2.i1-IQ3_XS.gguf b/Codex-24B-Small-3.2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..84c4872 --- /dev/null +++ b/Codex-24B-Small-3.2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61df8c15e573ab928d58cc51d3ff479f45b9fa68547516ef2578af6adf1b1765 +size 9907115744 diff --git a/Codex-24B-Small-3.2.i1-IQ4_XS.gguf b/Codex-24B-Small-3.2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..74e0cb1 --- /dev/null +++ b/Codex-24B-Small-3.2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e308eb55dfe9db4a098470b640dc22798da3390b7df8252d25dcf1583eeff674 +size 12758914784 diff --git a/Codex-24B-Small-3.2.i1-Q4_K_M.gguf b/Codex-24B-Small-3.2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..bf738cd --- /dev/null +++ b/Codex-24B-Small-3.2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a277956bab7ace2b8bacba2875570ad713ebbfa21ca2f44ed5cf1d7d2fc240c4 +size 14333908704 diff --git a/Codex-24B-Small-3.2.i1-Q5_K_M.gguf b/Codex-24B-Small-3.2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2d01c11 --- /dev/null +++ b/Codex-24B-Small-3.2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fc9f22230080d0ad29ac288684b8c58c1340b015c59e58eaf20b9c0c594834a +size 16763983584 diff --git a/Codex-24B-Small-3.2.i1-Q6_K.gguf b/Codex-24B-Small-3.2.i1-Q6_K.gguf new file mode 100644 index 0000000..d5290bc --- /dev/null +++ b/Codex-24B-Small-3.2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fa386a92441a4302c07e75c60634afbced4958c60e76c9b8342c6cd0cbec489 +size 19345938144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ec117d5 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Gryphe/Codex-24B-Small-3.2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- instruct +- finetune +- chatml +- axolotl +- roleplay +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Gryphe/Codex-24B-Small-3.2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Codex-24B-Small-3.2-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Codex-24B-Small-3.2-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://www.modelscope.cn/models/mradermacher/Codex-24B-Small-3.2-i1-GGUF/resolve/master/Codex-24B-Small-3.2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.3 | | +| [GGUF](https://www.modelscope.cn/models/mradermacher/Codex-24B-Small-3.2-i1-GGUF/resolve/master/Codex-24B-Small-3.2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.0 | | +| [GGUF](https://www.modelscope.cn/models/mradermacher/Codex-24B-Small-3.2-i1-GGUF/resolve/master/Codex-24B-Small-3.2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.9 | | +| [GGUF](https://www.modelscope.cn/models/mradermacher/Codex-24B-Small-3.2-i1-GGUF/resolve/master/Codex-24B-Small-3.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.4 | fast, recommended | +| [GGUF](https://www.modelscope.cn/models/mradermacher/Codex-24B-Small-3.2-i1-GGUF/resolve/master/Codex-24B-Small-3.2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 16.9 | | +| [GGUF](https://www.modelscope.cn/models/mradermacher/Codex-24B-Small-3.2-i1-GGUF/resolve/master/Codex-24B-Small-3.2.i1-Q6_K.gguf) | i1-Q6_K | 19.4 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + +