commit 89fe4f5f1bb251f849921f0783915f749d80c178 Author: ModelHub XC Date: Fri Oct 2 17:42:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..df1c456 --- /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 +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..168aa4d --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: mlfoundations-dev/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/mlfoundations-dev/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-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/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.f16.gguf) | f16 | 16.2 | 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/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.IQ4_XS.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.IQ4_XS.gguf new file mode 100644 index 0000000..8049b66 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b74c495be8f4dece00b310b47445050bf86f0f67876f5a6d2ad47af249d58b +size 4484364320 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q2_K.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q2_K.gguf new file mode 100644 index 0000000..488f686 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a294bfbdf615ca1eb3cc12108c88695598bc75e9a4c2a3f2c6bc4909a96097f4 +size 3179132960 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_L.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_L.gguf new file mode 100644 index 0000000..514563b --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b2c1c2499e1a97c63a7c14c8d145414fdffdfc13a6a59c951958a0ebf6a5ab7 +size 4321957920 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_M.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_M.gguf new file mode 100644 index 0000000..fb8a970 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf0e7efb65342af92e4c728500703a049ae092dff52570f9038a5bf114e4786c +size 4018919456 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_S.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_S.gguf new file mode 100644 index 0000000..449946f --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6491ba7854e12dfbfe94a77164491b16126065e852f210b2f7fad2f82ebe0be +size 3664500768 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q4_K_M.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q4_K_M.gguf new file mode 100644 index 0000000..7bd6235 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56d378448c8ea22308fceb98cabc9ca4bfe6d7ed64be89fa0dac756521cd2a46 +size 4920735776 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q4_K_S.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q4_K_S.gguf new file mode 100644 index 0000000..3e02d8e --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6afcc2bd60697af0f55a1a04caa042f47e85781f4d0976136da964e004452d06 +size 4692670496 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q5_K_M.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q5_K_M.gguf new file mode 100644 index 0000000..2ab4895 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a8c30581f3513aff5f9b55552f878034945d1249b14d08a70cc6e5b43b2876 +size 5732988960 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q5_K_S.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q5_K_S.gguf new file mode 100644 index 0000000..990a65e --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2bac897232be3bdf00dbe0c0858bbe8185e7d4c67471765ceb278e206f7b5a +size 5599295520 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q6_K.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q6_K.gguf new file mode 100644 index 0000000..b58bf90 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:defb8737954dbfb696f822405ad10de548fc931f8136fefe9ef2504bfcdd880f +size 6596007968 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q8_0.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q8_0.gguf new file mode 100644 index 0000000..f9cbe93 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22d87f5b0e6ab450cd91fd7eb9437a9b47046b352979cf11addf6ca61843812 +size 8540772384 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.f16.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.f16.gguf new file mode 100644 index 0000000..f23b240 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_8x.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee87a29c487e8187b0fc23cd26df939c1a465f04955c7d45577b618cee901979 +size 16068892704