commit 82489cad1ed9a1e3b6d1ebe4f66c5ab47898032d Author: ModelHub XC Date: Fri May 8 04:08:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a7a5897 --- /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 +dolphin-2.9.4-llama3.1-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..df48aa3 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: dphn/dolphin-2.9.4-llama3.1-8b +datasets: +- cognitivecomputations/Dolphin-2.9 +- m-a-p/CodeFeedback-Filtered-Instruction +- cognitivecomputations/dolphin-coder +- cognitivecomputations/samantha-data +- microsoft/orca-math-word-problems-200k +- mlabonne/FineTome-100k +- arcee/agent_data +- PawanKrd/math-gpt-4o-200k +- cognitivecomputations/SystemChat-2.0 +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/dphn/dolphin-2.9.4-llama3.1-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#dolphin-2.9.4-llama3.1-8b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-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/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.4-llama3.1-8b-GGUF/resolve/main/dolphin-2.9.4-llama3.1-8b.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. + + diff --git a/dolphin-2.9.4-llama3.1-8b.IQ3_M.gguf b/dolphin-2.9.4-llama3.1-8b.IQ3_M.gguf new file mode 100644 index 0000000..200bfab --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:976e2de458592c78e5fd42fb316db558d0bb86e90330097e378d5f6b37f6fa1f +size 3784834976 diff --git a/dolphin-2.9.4-llama3.1-8b.IQ3_S.gguf b/dolphin-2.9.4-llama3.1-8b.IQ3_S.gguf new file mode 100644 index 0000000..679ea26 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:405713f8c208aaba204dc5c03380ba1c446c58382391ddc7c90221f65569cba9 +size 3682336672 diff --git a/dolphin-2.9.4-llama3.1-8b.IQ3_XS.gguf b/dolphin-2.9.4-llama3.1-8b.IQ3_XS.gguf new file mode 100644 index 0000000..e0860c8 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ae48c4254f06f1189ce75ac0c37df79de0040a7498eeb89bc928644883c96f1 +size 3518758816 diff --git a/dolphin-2.9.4-llama3.1-8b.IQ4_XS.gguf b/dolphin-2.9.4-llama3.1-8b.IQ4_XS.gguf new file mode 100644 index 0000000..79a0fbc --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bed573712cc76b60b49e522ffb97d2d84db619fde3b25ab5668f77483d0cba3 +size 4484375264 diff --git a/dolphin-2.9.4-llama3.1-8b.Q2_K.gguf b/dolphin-2.9.4-llama3.1-8b.Q2_K.gguf new file mode 100644 index 0000000..e0052c0 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1732d4907ab1256b47ab503993a0cb2af3dabca6fc41d8d73fa1d4ae579bf4c1 +size 3179142240 diff --git a/dolphin-2.9.4-llama3.1-8b.Q3_K_L.gguf b/dolphin-2.9.4-llama3.1-8b.Q3_K_L.gguf new file mode 100644 index 0000000..b265ea1 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03c3b6548dd8f76bb0e7c068a1a823b6d89878bd4b73440a670d1f959a03aa79 +size 4321968032 diff --git a/dolphin-2.9.4-llama3.1-8b.Q3_K_M.gguf b/dolphin-2.9.4-llama3.1-8b.Q3_K_M.gguf new file mode 100644 index 0000000..96f0f7f --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5cbd1ecf4968176e5444b11d6e415fa904ce3640c95dd9479cc6a4d2e05c221 +size 4018929568 diff --git a/dolphin-2.9.4-llama3.1-8b.Q3_K_S.gguf b/dolphin-2.9.4-llama3.1-8b.Q3_K_S.gguf new file mode 100644 index 0000000..48fbe30 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:695c30bd3d495160d83c6509e2f07dafd00738b47b0919f8cf88cc74593468e7 +size 3664510880 diff --git a/dolphin-2.9.4-llama3.1-8b.Q4_K_M.gguf b/dolphin-2.9.4-llama3.1-8b.Q4_K_M.gguf new file mode 100644 index 0000000..71bc330 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7312b268548b112add70af51dbd9abc9659d969ab61e2030a3628ce20bdde406 +size 4920746976 diff --git a/dolphin-2.9.4-llama3.1-8b.Q4_K_S.gguf b/dolphin-2.9.4-llama3.1-8b.Q4_K_S.gguf new file mode 100644 index 0000000..f5bd4e1 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce32dbeae15ab2d4633fea655ed92268cd9261f0d869e0d2cf5db7e4afaead14 +size 4692681696 diff --git a/dolphin-2.9.4-llama3.1-8b.Q5_K_M.gguf b/dolphin-2.9.4-llama3.1-8b.Q5_K_M.gguf new file mode 100644 index 0000000..9ca543c --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e09917f91dcab060a09ed655dd4ee99c0d7b8b79740e97f0cfc2f099eab3bd +size 5733001184 diff --git a/dolphin-2.9.4-llama3.1-8b.Q5_K_S.gguf b/dolphin-2.9.4-llama3.1-8b.Q5_K_S.gguf new file mode 100644 index 0000000..c16b593 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fa5c27d5c3e073f61279039894a0e0c1bc908e3290849973e1cb566dc414402 +size 5599307744 diff --git a/dolphin-2.9.4-llama3.1-8b.Q6_K.gguf b/dolphin-2.9.4-llama3.1-8b.Q6_K.gguf new file mode 100644 index 0000000..32c7df2 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b151ec4d67e00292e86713920c8da33a4b519e25b9d9232af3f13dba95b561 +size 6596021280 diff --git a/dolphin-2.9.4-llama3.1-8b.Q8_0.gguf b/dolphin-2.9.4-llama3.1-8b.Q8_0.gguf new file mode 100644 index 0000000..6e59a56 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91945c943ada72bdf0c230599540a8d1ff7bac9495601c19ae28bbb4bf512511 +size 8540789664 diff --git a/dolphin-2.9.4-llama3.1-8b.f16.gguf b/dolphin-2.9.4-llama3.1-8b.f16.gguf new file mode 100644 index 0000000..03435f0 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eeefbcbec0b70bfb4e22d082e93a52193ffd50588c480b6a07023332ecde467 +size 16068925344