commit 87c60b7a924653d48c90e0e15a001df1cef6e7b3 Author: ModelHub XC Date: Mon May 4 13:20:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/h2o-danube3.1-4b-chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2a2bc53 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +h2o-danube3.1-4b-chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3.1-4b-chat.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8469cd6 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: h2oai/h2o-danube3.1-4b-chat +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- gpt +- llm +- large language model +- h2o-llmstudio +--- +## About + + + + + + +static quants of https://huggingface.co/h2oai/h2o-danube3.1-4b-chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-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/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.Q3_K_S.gguf) | Q3_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.IQ4_XS.gguf) | IQ4_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.4 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.Q4_K_S.gguf) | Q4_K_S | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.Q5_K_S.gguf) | Q5_K_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.Q8_0.gguf) | Q8_0 | 4.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3.1-4b-chat-GGUF/resolve/main/h2o-danube3.1-4b-chat.f16.gguf) | f16 | 8.0 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/h2o-danube3.1-4b-chat.IQ4_XS.gguf b/h2o-danube3.1-4b-chat.IQ4_XS.gguf new file mode 100644 index 0000000..0a98b73 --- /dev/null +++ b/h2o-danube3.1-4b-chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ddbfdf50c33fe9f6eb4484f313717aef2cabf84c654bfe28e917dabe99579d +size 2173888896 diff --git a/h2o-danube3.1-4b-chat.Q2_K.gguf b/h2o-danube3.1-4b-chat.Q2_K.gguf new file mode 100644 index 0000000..682296f --- /dev/null +++ b/h2o-danube3.1-4b-chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19e1a099068aafed71dcff1372a1ce355b76a887788015622ee1cb250b397a59 +size 1514407296 diff --git a/h2o-danube3.1-4b-chat.Q3_K_L.gguf b/h2o-danube3.1-4b-chat.Q3_K_L.gguf new file mode 100644 index 0000000..0e1b4a9 --- /dev/null +++ b/h2o-danube3.1-4b-chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20056e5dbaf83e0f7af34d8fc7d8b28e64a5352f94200587fb0df9a22dbab68f +size 2109108096 diff --git a/h2o-danube3.1-4b-chat.Q3_K_M.gguf b/h2o-danube3.1-4b-chat.Q3_K_M.gguf new file mode 100644 index 0000000..6fa4938 --- /dev/null +++ b/h2o-danube3.1-4b-chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c16de47deba56deda4bbf84f87f63720ac29aa3434cd993ecb60a7d93db68e0 +size 1941684096 diff --git a/h2o-danube3.1-4b-chat.Q3_K_S.gguf b/h2o-danube3.1-4b-chat.Q3_K_S.gguf new file mode 100644 index 0000000..5371950 --- /dev/null +++ b/h2o-danube3.1-4b-chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25c53660dba1d9e860fd8af1e56e3fc72532902c90f9d1a252bfad8ddd92436a +size 1751757696 diff --git a/h2o-danube3.1-4b-chat.Q4_0_4_4.gguf b/h2o-danube3.1-4b-chat.Q4_0_4_4.gguf new file mode 100644 index 0000000..d4421c6 --- /dev/null +++ b/h2o-danube3.1-4b-chat.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01a9ed7408877869eb7b11cedb52c3bd81858b40c114e6e36916dd64e70b08f3 +size 2261594496 diff --git a/h2o-danube3.1-4b-chat.Q4_K_M.gguf b/h2o-danube3.1-4b-chat.Q4_K_M.gguf new file mode 100644 index 0000000..06acdbd --- /dev/null +++ b/h2o-danube3.1-4b-chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f0d2b7dcc05decf5c1af0c36b8ac627baabcf289c41d5ffc2bc7a30c3731c47 +size 2394650496 diff --git a/h2o-danube3.1-4b-chat.Q4_K_S.gguf b/h2o-danube3.1-4b-chat.Q4_K_S.gguf new file mode 100644 index 0000000..c558b92 --- /dev/null +++ b/h2o-danube3.1-4b-chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a1d116483afd4b51320b26b6072475ec1bac1e75b91c20f86b8a199825b583a +size 2278183296 diff --git a/h2o-danube3.1-4b-chat.Q5_K_M.gguf b/h2o-danube3.1-4b-chat.Q5_K_M.gguf new file mode 100644 index 0000000..9be0e80 --- /dev/null +++ b/h2o-danube3.1-4b-chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa81d2e8908e02d50d50f4f89d976fab37e27411e702230dc298c5a87ae67426 +size 2809984896 diff --git a/h2o-danube3.1-4b-chat.Q5_K_S.gguf b/h2o-danube3.1-4b-chat.Q5_K_S.gguf new file mode 100644 index 0000000..3e8ac2d --- /dev/null +++ b/h2o-danube3.1-4b-chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f12fbffc0bf9a2b4971b9a4037ac9c73aebe5498c5b3f5849086500bd8db302 +size 2741440896 diff --git a/h2o-danube3.1-4b-chat.Q6_K.gguf b/h2o-danube3.1-4b-chat.Q6_K.gguf new file mode 100644 index 0000000..512ca09 --- /dev/null +++ b/h2o-danube3.1-4b-chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f3117e0ddebfb337b51c6bb47019a1413f6c7a82302809c95fbc67ab518d21f +size 3251277696 diff --git a/h2o-danube3.1-4b-chat.Q8_0.gguf b/h2o-danube3.1-4b-chat.Q8_0.gguf new file mode 100644 index 0000000..6abd381 --- /dev/null +++ b/h2o-danube3.1-4b-chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a19552f2bfb7f884f8d97d9f26f1251874ce7573093f1838fd79a7b4181211 +size 4210740096 diff --git a/h2o-danube3.1-4b-chat.f16.gguf b/h2o-danube3.1-4b-chat.f16.gguf new file mode 100644 index 0000000..ac1e900 --- /dev/null +++ b/h2o-danube3.1-4b-chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37569ec8d787369c42e11fed2f94925c4a3980137373ca304843de67cb1714cc +size 7924788096