commit 835223d0b6265121154a542fe759b1c774c93a22 Author: ModelHub XC Date: Mon Jul 13 03:45:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..de4dc72 --- /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 +NeuralReyna-Mini-1.8B-v0.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralReyna-Mini-1.8B-v0.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralReyna-Mini-1.8B-v0.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralReyna-Mini-1.8B-v0.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralReyna-Mini-1.8B-v0.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralReyna-Mini-1.8B-v0.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralReyna-Mini-1.8B-v0.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralReyna-Mini-1.8B-v0.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralReyna-Mini-1.8B-v0.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralReyna-Mini-1.8B-v0.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralReyna-Mini-1.8B-v0.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralReyna-Mini-1.8B-v0.2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralReyna-Mini-1.8B-v0.2.IQ4_XS.gguf b/NeuralReyna-Mini-1.8B-v0.2.IQ4_XS.gguf new file mode 100644 index 0000000..102379d --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8222633fb33a579085fc3c5be50d2718ad407a84312b36c29c8076eedd902a1c +size 1087362176 diff --git a/NeuralReyna-Mini-1.8B-v0.2.Q2_K.gguf b/NeuralReyna-Mini-1.8B-v0.2.Q2_K.gguf new file mode 100644 index 0000000..e3af08b --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0261d8e89bf37e603395cf48e0c5e02b341ac123a466138d78094e6ddfa15425 +size 846570624 diff --git a/NeuralReyna-Mini-1.8B-v0.2.Q3_K_L.gguf b/NeuralReyna-Mini-1.8B-v0.2.Q3_K_L.gguf new file mode 100644 index 0000000..816a659 --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9be78c132dbe1b9edcf37a67df88f45e1ae4c7d6b9ff75501bf96b45e9a93bb +size 1056201856 diff --git a/NeuralReyna-Mini-1.8B-v0.2.Q3_K_M.gguf b/NeuralReyna-Mini-1.8B-v0.2.Q3_K_M.gguf new file mode 100644 index 0000000..d3b8d23 --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4145064ebf063767e7e8ef0e63b703812d68c4e594406dcde3861738c39c131b +size 1015880832 diff --git a/NeuralReyna-Mini-1.8B-v0.2.Q3_K_S.gguf b/NeuralReyna-Mini-1.8B-v0.2.Q3_K_S.gguf new file mode 100644 index 0000000..ba4836b --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d547c92c70974d57e6ef5bbe478ff1755b92586ede419e7cc22bda227582326d +size 953572480 diff --git a/NeuralReyna-Mini-1.8B-v0.2.Q4_K_M.gguf b/NeuralReyna-Mini-1.8B-v0.2.Q4_K_M.gguf new file mode 100644 index 0000000..123a5e8 --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab6af061b0115c4a74e1ff98b0436ac26ae5824fafdcf3e31642f98e011ec638 +size 1217754240 diff --git a/NeuralReyna-Mini-1.8B-v0.2.Q4_K_S.gguf b/NeuralReyna-Mini-1.8B-v0.2.Q4_K_S.gguf new file mode 100644 index 0000000..24e62c0 --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cff081ba8d20a85769b584326d401340e826e14839cf4960b2d642ee55c68d2 +size 1158263936 diff --git a/NeuralReyna-Mini-1.8B-v0.2.Q5_K_M.gguf b/NeuralReyna-Mini-1.8B-v0.2.Q5_K_M.gguf new file mode 100644 index 0000000..e796d5f --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f05406b3f8a526713f8d4331777093e7e5982422b262b57e76a3351e024eca5b +size 1376777344 diff --git a/NeuralReyna-Mini-1.8B-v0.2.Q5_K_S.gguf b/NeuralReyna-Mini-1.8B-v0.2.Q5_K_S.gguf new file mode 100644 index 0000000..bb105c5 --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f681727145c1f45a239b67b98dea5ca3954293ab40d65c7aedf3c6c3fd9572b +size 1327821952 diff --git a/NeuralReyna-Mini-1.8B-v0.2.Q6_K.gguf b/NeuralReyna-Mini-1.8B-v0.2.Q6_K.gguf new file mode 100644 index 0000000..c12f2b4 --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4473835f296948827c4078f88d1ceb16f20a97def650cb1e1398cb06903c6c7 +size 1579027584 diff --git a/NeuralReyna-Mini-1.8B-v0.2.Q8_0.gguf b/NeuralReyna-Mini-1.8B-v0.2.Q8_0.gguf new file mode 100644 index 0000000..f505525 --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c80818dc88a5a85ecdc227b21d9a4b953b4f35d95515fd394dba505bb07a9b2 +size 1958304896 diff --git a/NeuralReyna-Mini-1.8B-v0.2.f16.gguf b/NeuralReyna-Mini-1.8B-v0.2.f16.gguf new file mode 100644 index 0000000..283fc8c --- /dev/null +++ b/NeuralReyna-Mini-1.8B-v0.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:316d55a55b8c1abc96bb87c1ba6f7d7c178dff9bf45ab403ffb53c0e34305cd0 +size 3680099456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..82979de --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: M4-ai/NeuralReyna-Mini-1.8B-v0.2 +datasets: +- Intel/orca_dpo_pairs +- Locutusque/Hercules-v3.0 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- conversational +--- +## About + + + + + + +static quants of https://huggingface.co/M4-ai/NeuralReyna-Mini-1.8B-v0.2 + + +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/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.IQ4_XS.gguf) | IQ4_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.Q5_K_M.gguf) | Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.Q8_0.gguf) | Q8_0 | 2.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralReyna-Mini-1.8B-v0.2-GGUF/resolve/main/NeuralReyna-Mini-1.8B-v0.2.f16.gguf) | f16 | 3.8 | 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. + +