commit 85cb74b8290e3d6351f489722433a2635aa5bfdb Author: ModelHub XC Date: Fri Sep 25 06:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Dolphin3.0-Llama3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e0da6fd --- /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-Llama3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin3.0-Llama3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Dolphin3.0-Llama3.2-3B.IQ4_XS.gguf b/Dolphin3.0-Llama3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..165044a --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea509f6efbbb139fc4aa9105518f56b4cde8a92cd9f7f2567535673e62c71378 +size 1840911680 diff --git a/Dolphin3.0-Llama3.2-3B.Q2_K.gguf b/Dolphin3.0-Llama3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..0685d6c --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a787e44669e27a98a93a9386ac7b7e4180e8eee920c6140f1fe1bfddf407f7ec +size 1363940672 diff --git a/Dolphin3.0-Llama3.2-3B.Q3_K_L.gguf b/Dolphin3.0-Llama3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..f45be24 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc9ad99a50d48d361a1cf5f86a320633701d8d6d2eed4c39b0ee15e8bd8e9ed3 +size 1815352640 diff --git a/Dolphin3.0-Llama3.2-3B.Q3_K_M.gguf b/Dolphin3.0-Llama3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..cf75b78 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:669ebeab023b1a5f77024258871e8d40f74a1ef50d48a31f727ffc419928328c +size 1687164224 diff --git a/Dolphin3.0-Llama3.2-3B.Q3_K_S.gguf b/Dolphin3.0-Llama3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..062154f --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2826741fe62e3984047b676aa81d57e0f4047e3ea4debc3327ac045ba753295 +size 1542853952 diff --git a/Dolphin3.0-Llama3.2-3B.Q4_K_M.gguf b/Dolphin3.0-Llama3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..c0bfc74 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48c5cf97be2817be6cde382a00480f33e39fdb5b87b40c4eb57dacc44a7759d +size 2019382592 diff --git a/Dolphin3.0-Llama3.2-3B.Q4_K_S.gguf b/Dolphin3.0-Llama3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..806e66f --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a411d63cf3fcd5c8c00a2023efe23414bebd07740ca7a431fb39cf06bc84ceeb +size 1928205632 diff --git a/Dolphin3.0-Llama3.2-3B.Q5_K_M.gguf b/Dolphin3.0-Llama3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..19a20d4 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039ebb01c9c5c0fbe8051fa6cea6ab3e850a5b00f7adaff031026a3dd88ea045 +size 2322158912 diff --git a/Dolphin3.0-Llama3.2-3B.Q5_K_S.gguf b/Dolphin3.0-Llama3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..dd66a89 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3e52b85d37054b01b6fea2347f208b280e417580e9455572be1fff9426354a8 +size 2269517120 diff --git a/Dolphin3.0-Llama3.2-3B.Q6_K.gguf b/Dolphin3.0-Llama3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..329e4cd --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4df28037d954bdd3fd2fcff705eba96e21d93afb13d8ae8474d228de988ba29b +size 2643858752 diff --git a/Dolphin3.0-Llama3.2-3B.Q8_0.gguf b/Dolphin3.0-Llama3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..6228408 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b013fa4f8d798569c620c5738f4ae4ea0aefcb87376dd4c68a9856d0611ddfea +size 3421905664 diff --git a/Dolphin3.0-Llama3.2-3B.f16.gguf b/Dolphin3.0-Llama3.2-3B.f16.gguf new file mode 100644 index 0000000..d2baba8 --- /dev/null +++ b/Dolphin3.0-Llama3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8fb04b1188a4504353bb638cea0b6cfb4fddd920d927a831c30b23d14a5f84 +size 6433700224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eb19bc5 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: dphn/Dolphin3.0-Llama3.2-3B +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-Llama3.2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Dolphin3.0-Llama3.2-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-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-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.2-3B-GGUF/resolve/main/Dolphin3.0-Llama3.2-3B.f16.gguf) | f16 | 6.5 | 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. + +