commit f360ca0e47511ff9eae6990a10a3ef969863758b Author: ModelHub XC Date: Sun Oct 18 15:54:19 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_0.5x-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..19a87e7 --- /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_0.5x.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.f16.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7dde4d2 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: mlfoundations-dev/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x +language: +- en +library_name: transformers +license: llama3.1 +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_0.5x + + +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_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.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_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.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_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.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_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.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_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.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_0.5x-GGUF/resolve/main/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.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_0.5x.IQ4_XS.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.IQ4_XS.gguf new file mode 100644 index 0000000..5f7ec60 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8f116d44a0ff27f123b03a7510e3c06540376c96714f260f320fd5e302f8bc1 +size 4484364352 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q2_K.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q2_K.gguf new file mode 100644 index 0000000..f0f51bf --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b68f933922d1a8198088109862e05395b584c4d51c1af3cb56bacaf972c6086 +size 3179132992 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_L.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_L.gguf new file mode 100644 index 0000000..fa35679 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af33bf616d6442a4de83ba8d9a311b71f28465ac76195c967d5a5ad0cb568cef +size 4321957952 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_M.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_M.gguf new file mode 100644 index 0000000..b70c9c9 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e11538eca103f6fc436a2c6c0e3f51990e68fe9dd14fca6f7fde05aaf8531f +size 4018919488 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_S.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_S.gguf new file mode 100644 index 0000000..4738e82 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6a551a9bc52ccba99b2cb570c664d02c16b43e05e39297baa20d9ebb799785c +size 3664500800 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q4_K_M.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q4_K_M.gguf new file mode 100644 index 0000000..548ec62 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828cd965d238399568485bd6e53a3162702aca40f915b66a956e097c944af407 +size 4920735808 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q4_K_S.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q4_K_S.gguf new file mode 100644 index 0000000..6d6a637 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3df222f14fdee27deefc592a5dfa11e64e6f1fa31723e215c1e40c425cc98c9d +size 4692670528 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q5_K_M.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q5_K_M.gguf new file mode 100644 index 0000000..789fdc6 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75272e5e14ac5c86dfa114d2dfb8622a13ac19f9b35f35001b88ac45e9557fc0 +size 5732988992 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q5_K_S.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q5_K_S.gguf new file mode 100644 index 0000000..2002d8a --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79f114e6acd35f93d20559aa04ed48f81c6166bc135d30241841571c24a316c0 +size 5599295552 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q6_K.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q6_K.gguf new file mode 100644 index 0000000..144eb97 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb9a245b644e42a6fc8b11622dd980709b68fdefc51aeee82299a5ed84bc4e86 +size 6596008000 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q8_0.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q8_0.gguf new file mode 100644 index 0000000..1f39246 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0390602b4361d19f3bdb966d7b6ed20a71137170e68c8fa9e7dba0d708a0ff0c +size 8540772416 diff --git a/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.f16.gguf b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.f16.gguf new file mode 100644 index 0000000..8e49640 --- /dev/null +++ b/oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b438ad38ab5cfa98fad0e2cec98cb019dda6a41b295cc85b4ab8b34d6332f98 +size 16068892736