commit fc0ae453844e50ce57347674bf6213395ef6551a Author: ModelHub XC Date: Thu Jun 18 15:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b23dd20 --- /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 +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..248de87 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Nexesenex/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct +datasets: +- llamafactory/alpaca_en +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- Llama-3 +- instruct +- finetune +- chatml +- gpt4 +- synthetic data +- distillation +- function calling +- json mode +- axolotl +- roleplaying +- chat +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct-GGUF/resolve/main/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.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. + + diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.IQ4_XS.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..cf51111 --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e7127e053935acf16de6430bc700c39882578e27125d52812f7efbf8ea23e47 +size 1840903584 diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q2_K.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..630a0e2 --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c1e06b9eb718e640c7f66c63933787e43573de7949781298f0a7a7e835c60ee +size 1363932576 diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_L.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..be7e3af --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b78f605df5c6e086d32dbfb34c42b6cc84af987d90a0bc46b199084caad018d3 +size 1815344544 diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_M.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..5969a11 --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be55941f84daecee8d985b75223a3a2a23ad301737b4f0787639ea6d8ee59e27 +size 1687156128 diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_S.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..bb0638b --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aa4ee21ff7d709c32ee376a620ebc7c0b3c785a1ea87574b8524197ba6c37a2 +size 1542845856 diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q4_K_M.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f9ae55a --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81002b80273af99a3260ed12a667a19a0c7e04aeb9d8fb4f5debf917ecf2a03a +size 2019374496 diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q4_K_S.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..60b6ce8 --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6002fdda8490a793a1e13f0764dfc585dfbe6f6e08bd73346aeed90b92f09a +size 1928197536 diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q5_K_M.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..2a9f329 --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c32076649d6b339bb1a7a146404d96dddf3d81be75dc36b9150e94a11df1e8 +size 2322150816 diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q5_K_S.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..8f1ac43 --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396ff9397dfd3d2779110a3cb67c9daebe328dc36cbe39b30edb9d4945b0de35 +size 2269509024 diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q6_K.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..38d0270 --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76496a29bd680eeeb2f30ea17bbe945e1c523468d9882824734e60c06ac371ef +size 2643850656 diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q8_0.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..72fdda4 --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f1ce22da98733cd84fed2c590be56a8bbfc494c1301c130c611ef32edb877f +size 3421896096 diff --git a/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.f16.gguf b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.f16.gguf new file mode 100644 index 0000000..08e057c --- /dev/null +++ b/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd54b68d27347196a623cfd9ffef01e3982766a5c175dbaa52884c9cbc3f553 +size 6433684896