commit 14bdc8dc69264e5a666a3fb7eeb802002f1f943c Author: ModelHub XC Date: Wed Jul 8 06:07:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: h2oai/h2o-danube2-1.8b-chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c724c6c --- /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-danube2-1.8b-chat-BF16.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-F16.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-F32.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +h2o-danube2-1.8b-chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c1bf254 --- /dev/null +++ b/README.md @@ -0,0 +1,54 @@ +--- +language: +- en +library_name: transformers +license: apache-2.0 +tags: +- gpt +- llm +- large language model +- h2o-llmstudio +thumbnail: >- + https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico +pipeline_tag: text-generation +quantized_by: h2oai +--- + +# h2o-danube2-1.8b-chat-GGUF +- Model creator: [H2O.ai](https://huggingface.co/h2oai) +- Original model: [h2o-danube2-1.8b-chat](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat) + +## Description + +This repo contains GGUF format model files for [h2o-danube2-1.8b-chat](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat) quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp/) framework. + +Table below summarizes different quantized versions of [h2o-danube2-1.8b-chat](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat). It shows the trade-off between size, speed and quality of the models. + + +| Name | Quant method | Model size | MT-Bench AVG | Perplexity | Tokens per second | +|:----------------------------------|:----------------------------------:|:----------:|:------------:|:------------:|:-------------------:| +| [h2o-danube2-1.8b-chat-F16.gguf](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-F16.gguf) | F16 | 3.66 GB | 5.60 | 8.02 | 797 | +| [h2o-danube2-1.8b-chat-Q8_0.gguf](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q8_0.gguf) | Q8_0 | 1.95 GB | 5.51 | 8.02 | 1156 | +| [h2o-danube2-1.8b-chat-Q6_K.gguf](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q6_K.gguf) | Q6_K | 1.50 GB | 5.51 | 8.03 | 1131 | +| [h2o-danube2-1.8b-chat-Q5_K_M.gguf](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q5_K_M.gguf) | Q5_K_M | 1.30 GB | 5.56 | 8.10 | 1172 | +| [h2o-danube2-1.8b-chat-Q5_K_S.gguf](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q5_K_S.gguf) | Q5_K_S | 1.27 GB | 5.49 | 8.12 | 1107 | +| [h2o-danube2-1.8b-chat-Q4_K_M.gguf](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q4_K_M.gguf) | Q4_K_M | 1.11 GB | 5.60 | 8.27 | 1162 | +| [h2o-danube2-1.8b-chat-Q4_K_S.gguf](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q4_K_S.gguf) | Q4_K_S | 1.06 GB | 5.59 | 8.34 | 1270 | +| [h2o-danube2-1.8b-chat-Q3_K_L.gguf](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q3_K_L.gguf) | Q3_K_L | 0.98 GB | 5.23 | 8.72 | 1442 | +| [h2o-danube2-1.8b-chat-Q3_K_M.gguf](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q3_K_M.gguf) | Q3_K_M | 0.91 GB | 4.91 | 8.81 | 1107 | +| [h2o-danube2-1.8b-chat-Q3_K_S.gguf](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q3_K_S.gguf) | Q3_K_S | 0.82 GB | 4.03 | 10.12 | 1103 | +| [h2o-danube2-1.8b-chat-Q2_K.gguf](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q2_K.gguf) | Q2_K | 0.71 GB | 3.03 | 12.56 | 1160 | + +Columns in the table are: +* Name -- model name and link +* Quant method -- quantization method +* Model size -- size of the model in gigabytes +* MT-Bench AVG -- [MT-Bench](https://arxiv.org/abs/2306.05685) benchmark score. The score is from 1 to 10, the higher, the better +* Perplexity -- perplexity metric on WikiText-2 dataset. It's reported in a perplexity test from llama.cpp. The lower, the better +* Tokens per second -- generation speed in tokens per second, as reported in a perplexity test from llama.cpp. The higher, the better. Speed tests are done on a single H100 GPU + + +## Prompt template +``` +<|prompt|>Why is drinking water so healthy?<|answer|> +``` diff --git a/h2o-danube2-1.8b-chat-BF16.gguf b/h2o-danube2-1.8b-chat-BF16.gguf new file mode 100644 index 0000000..ca24b44 --- /dev/null +++ b/h2o-danube2-1.8b-chat-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32c3307c2d32b09738291ad4979fee5aa6747531d8ad1d3fff0b3b37adedc7e +size 3663384736 diff --git a/h2o-danube2-1.8b-chat-F16.gguf b/h2o-danube2-1.8b-chat-F16.gguf new file mode 100644 index 0000000..e644082 --- /dev/null +++ b/h2o-danube2-1.8b-chat-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50831d27c3cf77162b106d1e376b614a57ee3cd52047f610375c13ac26956568 +size 3663384736 diff --git a/h2o-danube2-1.8b-chat-F32.gguf b/h2o-danube2-1.8b-chat-F32.gguf new file mode 100644 index 0000000..8cb70c3 --- /dev/null +++ b/h2o-danube2-1.8b-chat-F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9250414e7eda41e98036eac36c386ec95a73e7746d659c9579d94428113c1f98 +size 7325536416 diff --git a/h2o-danube2-1.8b-chat-Q2_K.gguf b/h2o-danube2-1.8b-chat-Q2_K.gguf new file mode 100644 index 0000000..2f985fd --- /dev/null +++ b/h2o-danube2-1.8b-chat-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:767ad89549bc3d26fa2434eb68988685af1af6bf902887d2b1c794a777be5357 +size 710696096 diff --git a/h2o-danube2-1.8b-chat-Q3_K_L.gguf b/h2o-danube2-1.8b-chat-Q3_K_L.gguf new file mode 100644 index 0000000..f09229b --- /dev/null +++ b/h2o-danube2-1.8b-chat-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3fd561517bc4f4b93dd7d185e5d49d32c44b717c65c90b63a6c32b9d6469a8c +size 980197536 diff --git a/h2o-danube2-1.8b-chat-Q3_K_M.gguf b/h2o-danube2-1.8b-chat-Q3_K_M.gguf new file mode 100644 index 0000000..faa96ec --- /dev/null +++ b/h2o-danube2-1.8b-chat-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e61e22933e5aaed3e5a39a07505ccabf92c1433e23ac3b1deaac3538ad382f05 +size 905158816 diff --git a/h2o-danube2-1.8b-chat-Q3_K_S.gguf b/h2o-danube2-1.8b-chat-Q3_K_S.gguf new file mode 100644 index 0000000..9e59362 --- /dev/null +++ b/h2o-danube2-1.8b-chat-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa3a4f58184948b28aea25ee1929051e308987f22db0a7259cce3348954937e3 +size 820023456 diff --git a/h2o-danube2-1.8b-chat-Q4_K_M.gguf b/h2o-danube2-1.8b-chat-Q4_K_M.gguf new file mode 100644 index 0000000..00f5159 --- /dev/null +++ b/h2o-danube2-1.8b-chat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a303ee6b94a961aa43e48eb11629e933c4438fae5e6db336318a5d33fe57d79 +size 1112145056 diff --git a/h2o-danube2-1.8b-chat-Q4_K_S.gguf b/h2o-danube2-1.8b-chat-Q4_K_S.gguf new file mode 100644 index 0000000..4d90efb --- /dev/null +++ b/h2o-danube2-1.8b-chat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a048e0f5c962e1806e70dfd552c5b828566c11564ef64a4fb563eacc16689f37 +size 1059787936 diff --git a/h2o-danube2-1.8b-chat-Q5_K_M.gguf b/h2o-danube2-1.8b-chat-Q5_K_M.gguf new file mode 100644 index 0000000..0d774d1 --- /dev/null +++ b/h2o-danube2-1.8b-chat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b2c4614e6d17e3cb3906af15b63ebccdee0d81c0b12f98147a686420f41624e +size 1301789856 diff --git a/h2o-danube2-1.8b-chat-Q5_K_S.gguf b/h2o-danube2-1.8b-chat-Q5_K_S.gguf new file mode 100644 index 0000000..b9dde0e --- /dev/null +++ b/h2o-danube2-1.8b-chat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8d38f0cd44c912733fd12c082f299e4031a505356cccfe916b8f869fabf5587 +size 1270977696 diff --git a/h2o-danube2-1.8b-chat-Q6_K.gguf b/h2o-danube2-1.8b-chat-Q6_K.gguf new file mode 100644 index 0000000..bf58002 --- /dev/null +++ b/h2o-danube2-1.8b-chat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7351be91a81820b22cafeaddf8b41264c94db2bbd0bfa1fafe6d7cf99bd02c5e +size 1503287456 diff --git a/h2o-danube2-1.8b-chat-Q8_0.gguf b/h2o-danube2-1.8b-chat-Q8_0.gguf new file mode 100644 index 0000000..e84f135 --- /dev/null +++ b/h2o-danube2-1.8b-chat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa220da02f3d09dc430bf8eb92ab73510ad65a52bc6366448867e84a855c9ec +size 1946751136