commit 1584efb9e63ef1b44fe3c5db3002310d7a21916b Author: ModelHub XC Date: Tue Sep 15 15:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ADT-LLama31-Training-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9691b12 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +ADT-LLama31-Training.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.f16.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ADT-LLama31-Training.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ADT-LLama31-Training.IQ3_M.gguf b/ADT-LLama31-Training.IQ3_M.gguf new file mode 100644 index 0000000..cd42c62 --- /dev/null +++ b/ADT-LLama31-Training.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d32d8ab595ab81ffefceef1a89ac8bae610fcab1f0c7bc926318422dbd29a24e +size 3784824192 diff --git a/ADT-LLama31-Training.IQ3_S.gguf b/ADT-LLama31-Training.IQ3_S.gguf new file mode 100644 index 0000000..b7be8ae --- /dev/null +++ b/ADT-LLama31-Training.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f20e2ecaace70c2598401a1c1718cc33bfcb0f7b3b000fc16aef7c22a2cafd4 +size 3682325888 diff --git a/ADT-LLama31-Training.IQ3_XS.gguf b/ADT-LLama31-Training.IQ3_XS.gguf new file mode 100644 index 0000000..bfaaf78 --- /dev/null +++ b/ADT-LLama31-Training.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2c34440f183314fb1e2b7a95d6afb2c7a38a41d290eb6e10d744cab3793986 +size 3518748032 diff --git a/ADT-LLama31-Training.IQ4_XS.gguf b/ADT-LLama31-Training.IQ4_XS.gguf new file mode 100644 index 0000000..79fcfdf --- /dev/null +++ b/ADT-LLama31-Training.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:774c76f602c1049aa84130da96924f3033d42e65c22f0a3563d6c0a560891458 +size 4484363648 diff --git a/ADT-LLama31-Training.Q2_K.gguf b/ADT-LLama31-Training.Q2_K.gguf new file mode 100644 index 0000000..ed9b975 --- /dev/null +++ b/ADT-LLama31-Training.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77015ed15a8ee9bec07086203104f6e4ef5956d3ddd550ee7441c0d8062ed08e +size 3179132288 diff --git a/ADT-LLama31-Training.Q3_K_L.gguf b/ADT-LLama31-Training.Q3_K_L.gguf new file mode 100644 index 0000000..347d53d --- /dev/null +++ b/ADT-LLama31-Training.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89029f56eb0bece4ebd59b918737ceeb6aad8c5bc5900544a1d9af734f0ab618 +size 4321957248 diff --git a/ADT-LLama31-Training.Q3_K_M.gguf b/ADT-LLama31-Training.Q3_K_M.gguf new file mode 100644 index 0000000..7594767 --- /dev/null +++ b/ADT-LLama31-Training.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d723ca35439c5b2cc7a9544ee2a045fa3130c27a49b326c48ec8a68910681b53 +size 4018918784 diff --git a/ADT-LLama31-Training.Q3_K_S.gguf b/ADT-LLama31-Training.Q3_K_S.gguf new file mode 100644 index 0000000..98de778 --- /dev/null +++ b/ADT-LLama31-Training.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:687ba0b21726189de74ac6bc7fa12bb070ba0672ae9c5de46f325a266436fb73 +size 3664500096 diff --git a/ADT-LLama31-Training.Q4_K_M.gguf b/ADT-LLama31-Training.Q4_K_M.gguf new file mode 100644 index 0000000..ecd89d7 --- /dev/null +++ b/ADT-LLama31-Training.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1309413007097d7f2c813847ea77c6f8923f175d151b3679280838ba4470e388 +size 4920735104 diff --git a/ADT-LLama31-Training.Q4_K_S.gguf b/ADT-LLama31-Training.Q4_K_S.gguf new file mode 100644 index 0000000..cbd9dd4 --- /dev/null +++ b/ADT-LLama31-Training.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a1e7b0a6f607701625c95cd574ba1cda8932fe03eedcd4622b94bdf97901d4f +size 4692669824 diff --git a/ADT-LLama31-Training.Q5_K_M.gguf b/ADT-LLama31-Training.Q5_K_M.gguf new file mode 100644 index 0000000..ddf2e9c --- /dev/null +++ b/ADT-LLama31-Training.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48c8a7f54aebac12b71c7ccafa8b4644ba76bd62a4f0f592188b0bc24d402210 +size 5732988288 diff --git a/ADT-LLama31-Training.Q5_K_S.gguf b/ADT-LLama31-Training.Q5_K_S.gguf new file mode 100644 index 0000000..9ca22fe --- /dev/null +++ b/ADT-LLama31-Training.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4d49780ac1f277a40c56998fd2333a148842dc53514e750fc7213c5596a452 +size 5599294848 diff --git a/ADT-LLama31-Training.Q6_K.gguf b/ADT-LLama31-Training.Q6_K.gguf new file mode 100644 index 0000000..9517933 --- /dev/null +++ b/ADT-LLama31-Training.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa906d6c63ef01a79c4a816220f5250d89ec74b8bc9aab7a46992a19197353f5 +size 6596007296 diff --git a/ADT-LLama31-Training.Q8_0.gguf b/ADT-LLama31-Training.Q8_0.gguf new file mode 100644 index 0000000..84dddfe --- /dev/null +++ b/ADT-LLama31-Training.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82f7acda31d46b5ee57c388094b9554441d96599f50b1c9873ff845e6a07f389 +size 8540771712 diff --git a/ADT-LLama31-Training.f16.gguf b/ADT-LLama31-Training.f16.gguf new file mode 100644 index 0000000..2637f53 --- /dev/null +++ b/ADT-LLama31-Training.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:221e9c21e8768ff69e4beb7dcebbca42ceaace56998cfad25bab8a45c7c6c68f +size 16068892032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..df7c893 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Nexling/ADT-LLama31-Training +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Nexling/ADT-LLama31-Training + + +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/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ADT-LLama31-Training-GGUF/resolve/main/ADT-LLama31-Training.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. + +