commit 4d3209e911ddb6bcc9f13243c32409ee73bd35fe Author: ModelHub XC Date: Fri Jun 12 11:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3161f76 --- /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 +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9a8c02c --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: mlfoundations-dev/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp +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/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-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/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF/resolve/main/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.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/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.IQ4_XS.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.IQ4_XS.gguf new file mode 100644 index 0000000..57d7ba8 --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d37aefc9ab3dc5ff509f4232b52900c4b92b4510763341fb62dfe62ffd159b +size 4484364352 diff --git a/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q2_K.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q2_K.gguf new file mode 100644 index 0000000..c43cabc --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36fb33f084796e41bd3e8d7d87574d558489fee426e73b9ab038e54a8f2775a7 +size 3179132992 diff --git a/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_L.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_L.gguf new file mode 100644 index 0000000..e056a75 --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc2d37a8f11c27dbb4c1e2fb5d67abce7ebaab02d12b20b9f541b0d66874d25e +size 4321957952 diff --git a/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_M.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_M.gguf new file mode 100644 index 0000000..f0a6295 --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0071df27b8c53fce0b550d08464da540e97d98cde502a04811e7388c8d49f14 +size 4018919488 diff --git a/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_S.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_S.gguf new file mode 100644 index 0000000..7fff07f --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d525269ccac43b6986f7397ba650f3b036148fe3d5bff4448486da5ef2c09ba3 +size 3664500800 diff --git a/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q4_K_M.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q4_K_M.gguf new file mode 100644 index 0000000..545c3d2 --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb1747d7359dec489be64085651fcd8070b036ac42db85d4a2b27d71e1226a9 +size 4920735808 diff --git a/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q4_K_S.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q4_K_S.gguf new file mode 100644 index 0000000..fe79919 --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c00a9c10492104b95debe036c6704a57e7be7dd0505438aac97c4bb0f01d6b +size 4692670528 diff --git a/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q5_K_M.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q5_K_M.gguf new file mode 100644 index 0000000..296666e --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc15b8204a7ddd40bbcd8ed653b43e333bc6ce64b23388f8c66b6af355ca8c5 +size 5732988992 diff --git a/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q5_K_S.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q5_K_S.gguf new file mode 100644 index 0000000..e65319b --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f281cdaee46c42433708dc461afa5212ae107662b409769507384772ace73f +size 5599295552 diff --git a/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q6_K.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q6_K.gguf new file mode 100644 index 0000000..80f38f0 --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6502e8260f564e5bbeba3f0b59b5a5bc4e558ec7e6fcf742d2f1a2e2cad7390 +size 6596008000 diff --git a/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q8_0.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q8_0.gguf new file mode 100644 index 0000000..4a0855f --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b43eb66c6d190dd73a22a51783c459ee166944ca458b311464c6e7d316214af5 +size 8540772416 diff --git a/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.f16.gguf b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.f16.gguf new file mode 100644 index 0000000..e18177a --- /dev/null +++ b/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5d1835bd11006a7f08e8f6a4fe57c66a52798ccb0ee0118e546626eeb68d8b5 +size 16068892736