commit ac63e71ba2088707d73555b1e283228ec866a55f Author: ModelHub XC Date: Thu Apr 23 22:24:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/h2o-danube3-4b-chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6480870 --- /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 +h2o-danube3-4b-chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3-4b-chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3-4b-chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3-4b-chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3-4b-chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3-4b-chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3-4b-chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3-4b-chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3-4b-chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3-4b-chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3-4b-chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube3-4b-chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5c0dfc0 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: h2oai/h2o-danube3-4b-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-danube3-4b-chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/h2o-danube3-4b-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-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-chat.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-chat.Q3_K_S.gguf) | Q3_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-chat.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-chat.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-chat.IQ4_XS.gguf) | IQ4_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-chat.Q4_K_S.gguf) | Q4_K_S | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-chat.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-chat.Q5_K_S.gguf) | Q5_K_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-chat.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-chat.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-chat.Q8_0.gguf) | Q8_0 | 4.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/h2o-danube3-4b-chat-GGUF/resolve/main/h2o-danube3-4b-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. + + diff --git a/h2o-danube3-4b-chat.IQ4_XS.gguf b/h2o-danube3-4b-chat.IQ4_XS.gguf new file mode 100644 index 0000000..03ee8a8 --- /dev/null +++ b/h2o-danube3-4b-chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e4f4e259480b6e8b0e17fe2286de6e461c6e4fa6fed626c13c1148a29967dc5 +size 2173888288 diff --git a/h2o-danube3-4b-chat.Q2_K.gguf b/h2o-danube3-4b-chat.Q2_K.gguf new file mode 100644 index 0000000..b67e7a0 --- /dev/null +++ b/h2o-danube3-4b-chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53de6446bec9ce5ab100b18771984103f99707d665c5b127cca6edd67c624cdc +size 1514406688 diff --git a/h2o-danube3-4b-chat.Q3_K_L.gguf b/h2o-danube3-4b-chat.Q3_K_L.gguf new file mode 100644 index 0000000..a7874e7 --- /dev/null +++ b/h2o-danube3-4b-chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42b18dcb3879ea0495cf5e14e3429a447208b18265b4a8ddcfc04aa4148dd68a +size 2109107488 diff --git a/h2o-danube3-4b-chat.Q3_K_M.gguf b/h2o-danube3-4b-chat.Q3_K_M.gguf new file mode 100644 index 0000000..dec88a7 --- /dev/null +++ b/h2o-danube3-4b-chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b808823f03dd026aa2976efb1bbe474827e776881cae4490866cd4b590d99cf5 +size 1941683488 diff --git a/h2o-danube3-4b-chat.Q3_K_S.gguf b/h2o-danube3-4b-chat.Q3_K_S.gguf new file mode 100644 index 0000000..1c23027 --- /dev/null +++ b/h2o-danube3-4b-chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf71bb25d291fd416c79f9978b981923894f2e34457a551901da74297f4d325d +size 1751757088 diff --git a/h2o-danube3-4b-chat.Q4_K_M.gguf b/h2o-danube3-4b-chat.Q4_K_M.gguf new file mode 100644 index 0000000..41e140e --- /dev/null +++ b/h2o-danube3-4b-chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f763600012c974e233f0f4cebd9c01b1832560a6fff4e009428da8d243e833d +size 2394649888 diff --git a/h2o-danube3-4b-chat.Q4_K_S.gguf b/h2o-danube3-4b-chat.Q4_K_S.gguf new file mode 100644 index 0000000..ccdda2e --- /dev/null +++ b/h2o-danube3-4b-chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d421376049aa56f66e4986a853ccc17f1a64adf08a5e01269863b72a80b29d17 +size 2278182688 diff --git a/h2o-danube3-4b-chat.Q5_K_M.gguf b/h2o-danube3-4b-chat.Q5_K_M.gguf new file mode 100644 index 0000000..48c0de2 --- /dev/null +++ b/h2o-danube3-4b-chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d28e34fb9b4f7130d0ee9cd6964bcfd345e83caf198a0320d826558b1c5601c3 +size 2809984288 diff --git a/h2o-danube3-4b-chat.Q5_K_S.gguf b/h2o-danube3-4b-chat.Q5_K_S.gguf new file mode 100644 index 0000000..285d900 --- /dev/null +++ b/h2o-danube3-4b-chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cf4dfdcf860ae67a55a298b51d35e6219a5aff97a12f68d512547c22f5445d7 +size 2741440288 diff --git a/h2o-danube3-4b-chat.Q6_K.gguf b/h2o-danube3-4b-chat.Q6_K.gguf new file mode 100644 index 0000000..aab8aad --- /dev/null +++ b/h2o-danube3-4b-chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14f88aaa756f0817d69e4843ea741adb1f97d08d68bcaa78a36259a57d20f45d +size 3251277088 diff --git a/h2o-danube3-4b-chat.Q8_0.gguf b/h2o-danube3-4b-chat.Q8_0.gguf new file mode 100644 index 0000000..605c1ee --- /dev/null +++ b/h2o-danube3-4b-chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4dfb250312a6ab68b5579b28d92a0f9723c9afb553864fb100f43ec05678ee5 +size 4210739488 diff --git a/h2o-danube3-4b-chat.f16.gguf b/h2o-danube3-4b-chat.f16.gguf new file mode 100644 index 0000000..a0c6fe8 --- /dev/null +++ b/h2o-danube3-4b-chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:079d0ffcd25a6eebb9fdd9d165fa858720a605ba64d378f0bcfc8618e20c8cdc +size 7924787488