commit 5d903155d2b4416a8b6f5a9b9d030d7e6dde8228 Author: ModelHub XC Date: Fri Jul 10 20:10:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Diogenes-12B-ChatMLified-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c72fee8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Diogenes-12B-ChatMLified.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Diogenes-12B-ChatMLified.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Diogenes-12B-ChatMLified.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Diogenes-12B-ChatMLified.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Diogenes-12B-ChatMLified.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Diogenes-12B-ChatMLified.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Diogenes-12B-ChatMLified.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Diogenes-12B-ChatMLified.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Diogenes-12B-ChatMLified.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Diogenes-12B-ChatMLified.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Diogenes-12B-ChatMLified.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Diogenes-12B-ChatMLified.IQ4_XS.gguf b/Diogenes-12B-ChatMLified.IQ4_XS.gguf new file mode 100644 index 0000000..e69b488 --- /dev/null +++ b/Diogenes-12B-ChatMLified.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b73e74bbaf6cabe5f47490155a5e1341ca1b7ac01ae896e5624308dd75996e +size 6800053472 diff --git a/Diogenes-12B-ChatMLified.Q2_K.gguf b/Diogenes-12B-ChatMLified.Q2_K.gguf new file mode 100644 index 0000000..bc7abdd --- /dev/null +++ b/Diogenes-12B-ChatMLified.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:231c6b3cd50f9e1d4401520650db4bbf22800a1d9984cf163370ff0722c94188 +size 4791047392 diff --git a/Diogenes-12B-ChatMLified.Q3_K_L.gguf b/Diogenes-12B-ChatMLified.Q3_K_L.gguf new file mode 100644 index 0000000..7831a52 --- /dev/null +++ b/Diogenes-12B-ChatMLified.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b6bcbd65f0dd0fbe1dca0e90ad82ada04be7b7044a40f4a86a109718f45e72f +size 6561502432 diff --git a/Diogenes-12B-ChatMLified.Q3_K_M.gguf b/Diogenes-12B-ChatMLified.Q3_K_M.gguf new file mode 100644 index 0000000..da418a8 --- /dev/null +++ b/Diogenes-12B-ChatMLified.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce06ccf6538600fd2a10fb93bf9e1edc1663b5cf56e88d62326820d1bf4073ed +size 6083089632 diff --git a/Diogenes-12B-ChatMLified.Q3_K_S.gguf b/Diogenes-12B-ChatMLified.Q3_K_S.gguf new file mode 100644 index 0000000..b9507f1 --- /dev/null +++ b/Diogenes-12B-ChatMLified.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56432c63647eb81b8b3f094636503bfc34fbf6e61281cc260387bb86ac74187e +size 5534225632 diff --git a/Diogenes-12B-ChatMLified.Q4_K_M.gguf b/Diogenes-12B-ChatMLified.Q4_K_M.gguf new file mode 100644 index 0000000..386ec86 --- /dev/null +++ b/Diogenes-12B-ChatMLified.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e0ce20a3c38d67ec5b60d10e550387a0103ec7ebc3a84e063508b7278d086ae +size 7477204192 diff --git a/Diogenes-12B-ChatMLified.Q4_K_S.gguf b/Diogenes-12B-ChatMLified.Q4_K_S.gguf new file mode 100644 index 0000000..f01df13 --- /dev/null +++ b/Diogenes-12B-ChatMLified.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45bcd6df7e3349b6c9b85e53be14c3d3e191982eaddcd575ec876635ff3fa2d3 +size 7120196832 diff --git a/Diogenes-12B-ChatMLified.Q5_K_M.gguf b/Diogenes-12B-ChatMLified.Q5_K_M.gguf new file mode 100644 index 0000000..706fb5c --- /dev/null +++ b/Diogenes-12B-ChatMLified.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0ca4ba9a40a26f011cb3d3790a888cc9c2f77b04fdcf740a6b23f4c78687611 +size 8727631072 diff --git a/Diogenes-12B-ChatMLified.Q5_K_S.gguf b/Diogenes-12B-ChatMLified.Q5_K_S.gguf new file mode 100644 index 0000000..c22ca13 --- /dev/null +++ b/Diogenes-12B-ChatMLified.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d332cd403901787088eb285694cd6c1d2381ccc7be28b3bd86a99e053bfaffcc +size 8518735072 diff --git a/Diogenes-12B-ChatMLified.Q6_K.gguf b/Diogenes-12B-ChatMLified.Q6_K.gguf new file mode 100644 index 0000000..a1ff8e9 --- /dev/null +++ b/Diogenes-12B-ChatMLified.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350235251548c8c92818e37aa353a4bcecbbffae507b599b4ac28c26d32b5113 +size 10056209632 diff --git a/Diogenes-12B-ChatMLified.Q8_0.gguf b/Diogenes-12B-ChatMLified.Q8_0.gguf new file mode 100644 index 0000000..72c5290 --- /dev/null +++ b/Diogenes-12B-ChatMLified.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a09505c3d4158f704918ee15ea5a3d6a09c5df06dc816786420cb1283923f1a7 +size 13022368992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b8f54d1 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Nitral-Archive/Diogenes-12B-ChatMLified +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Nitral-Archive/Diogenes-12B-ChatMLified + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Diogenes-12B-ChatMLified-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-i1-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://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-GGUF/resolve/main/Diogenes-12B-ChatMLified.Q2_K.gguf) | Q2_K | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-GGUF/resolve/main/Diogenes-12B-ChatMLified.Q3_K_S.gguf) | Q3_K_S | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-GGUF/resolve/main/Diogenes-12B-ChatMLified.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-GGUF/resolve/main/Diogenes-12B-ChatMLified.Q3_K_L.gguf) | Q3_K_L | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-GGUF/resolve/main/Diogenes-12B-ChatMLified.IQ4_XS.gguf) | IQ4_XS | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-GGUF/resolve/main/Diogenes-12B-ChatMLified.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-GGUF/resolve/main/Diogenes-12B-ChatMLified.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-GGUF/resolve/main/Diogenes-12B-ChatMLified.Q5_K_S.gguf) | Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-GGUF/resolve/main/Diogenes-12B-ChatMLified.Q5_K_M.gguf) | Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-GGUF/resolve/main/Diogenes-12B-ChatMLified.Q6_K.gguf) | Q6_K | 10.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Diogenes-12B-ChatMLified-GGUF/resolve/main/Diogenes-12B-ChatMLified.Q8_0.gguf) | Q8_0 | 13.1 | fast, best quality | + +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. + +