commit 2eb3d61c4e740e5f9bfb40d1b721f59bdea6805f Author: ModelHub XC Date: Thu Oct 22 11:55:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Dolphin3.0-Llama3.2-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bbe7be8 --- /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 +Dolphin3.0-Llama3.2-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Dolphin3.0-Llama3.2-1B.IQ4_XS.gguf b/Dolphin3.0-Llama3.2-1B.IQ4_XS.gguf new file mode 100644 index 0000000..25f1b74 --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aa70c3fa3a3dae6f3e53b18d9ff6965748f47e814cbcec831bdedbf8742e447 +size 748387552 diff --git a/Dolphin3.0-Llama3.2-1B.Q2_K.gguf b/Dolphin3.0-Llama3.2-1B.Q2_K.gguf new file mode 100644 index 0000000..bcedfc7 --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bbcc93c41c1734c00cfa5fd3984b072f9abcc238f00cde2f772d454c71f09cd +size 580877536 diff --git a/Dolphin3.0-Llama3.2-1B.Q3_K_L.gguf b/Dolphin3.0-Llama3.2-1B.Q3_K_L.gguf new file mode 100644 index 0000000..55b84ef --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84afc8b9fb277fb40ce82d751d2fe9749e1829260f097a4bd19c841e01b6d0bc +size 732527840 diff --git a/Dolphin3.0-Llama3.2-1B.Q3_K_M.gguf b/Dolphin3.0-Llama3.2-1B.Q3_K_M.gguf new file mode 100644 index 0000000..960d7a8 --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3be6fdde9d7a0062c9ca74a69f64f2617fdeddb95a12f1e1e05ecd91b8081b96 +size 690846944 diff --git a/Dolphin3.0-Llama3.2-1B.Q3_K_S.gguf b/Dolphin3.0-Llama3.2-1B.Q3_K_S.gguf new file mode 100644 index 0000000..f700b07 --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5309e4bc7ee928e267c4bfbe5e0bfe0f7ae07801e9862b4ba808101a8be3a60 +size 641694944 diff --git a/Dolphin3.0-Llama3.2-1B.Q4_K_M.gguf b/Dolphin3.0-Llama3.2-1B.Q4_K_M.gguf new file mode 100644 index 0000000..613a535 --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c43a77263bf29488069044a7ccfa2c8d45b592c220104c559050bc89decd8a +size 807697632 diff --git a/Dolphin3.0-Llama3.2-1B.Q4_K_S.gguf b/Dolphin3.0-Llama3.2-1B.Q4_K_S.gguf new file mode 100644 index 0000000..f564b96 --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38ecee6b8dbc4e063f1186fcf64a7f38434ee1bd6d77972fac9a53bb3a9e2cbd +size 775650528 diff --git a/Dolphin3.0-Llama3.2-1B.Q5_K_M.gguf b/Dolphin3.0-Llama3.2-1B.Q5_K_M.gguf new file mode 100644 index 0000000..04fb580 --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a1f832a40a4008a0406cf162c642158a2573e1b0056e38d713835051d9efdf +size 911506656 diff --git a/Dolphin3.0-Llama3.2-1B.Q5_K_S.gguf b/Dolphin3.0-Llama3.2-1B.Q5_K_S.gguf new file mode 100644 index 0000000..afc5c19 --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc7aa6927d853cf77440abc099292380bc57653c8ca1b44af666bd2dfa0b79af +size 892566752 diff --git a/Dolphin3.0-Llama3.2-1B.Q6_K.gguf b/Dolphin3.0-Llama3.2-1B.Q6_K.gguf new file mode 100644 index 0000000..4fa1ec3 --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43e2feeefb2f7cbf8e01000ba65b7bb51cfebad45fc20ebf369e127bc328c098 +size 1021803744 diff --git a/Dolphin3.0-Llama3.2-1B.Q8_0.gguf b/Dolphin3.0-Llama3.2-1B.Q8_0.gguf new file mode 100644 index 0000000..9f796af --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd38b02d958f3002e302d280da0fa8f71b8cfb0be19b0210306d99645dc5fba3 +size 1321087168 diff --git a/Dolphin3.0-Llama3.2-1B.f16.gguf b/Dolphin3.0-Llama3.2-1B.f16.gguf new file mode 100644 index 0000000..694aff5 --- /dev/null +++ b/Dolphin3.0-Llama3.2-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82f31ebbdb463bb492a335672b318923a4a466af7fda47cabdabf54918dc7bae +size 2479603648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..67826a4 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: dphn/Dolphin3.0-Llama3.2-1B +datasets: +- OpenCoder-LLM/opc-sft-stage1 +- OpenCoder-LLM/opc-sft-stage2 +- microsoft/orca-agentinstruct-1M-v1 +- microsoft/orca-math-word-problems-200k +- NousResearch/hermes-function-calling-v1 +- AI-MO/NuminaMath-CoT +- AI-MO/NuminaMath-TIR +- allenai/tulu-3-sft-mixture +- cognitivecomputations/dolphin-coder +- HuggingFaceTB/smoltalk +- cognitivecomputations/samantha-data +- m-a-p/CodeFeedback-Filtered-Instruction +- m-a-p/Code-Feedback +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/dphn/Dolphin3.0-Llama3.2-1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Dolphin3.0-Llama3.2-1B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-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/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-1B-GGUF/resolve/main/Dolphin3.0-Llama3.2-1B.f16.gguf) | f16 | 2.6 | 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. + +