commit 4f86606742230cb6a0338620bed99cc2206e5e2e Author: ModelHub XC Date: Sat Oct 24 06:24:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hamanasu-Magnum-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d2df20a --- /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 +Hamanasu-Magnum-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hamanasu-Magnum-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hamanasu-Magnum-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hamanasu-Magnum-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hamanasu-Magnum-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hamanasu-Magnum-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hamanasu-Magnum-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hamanasu-Magnum-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hamanasu-Magnum-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hamanasu-Magnum-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hamanasu-Magnum-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hamanasu-Magnum-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hamanasu-Magnum-4B.IQ4_XS.gguf b/Hamanasu-Magnum-4B.IQ4_XS.gguf new file mode 100644 index 0000000..eceabea --- /dev/null +++ b/Hamanasu-Magnum-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10b2e74b89e562f554336d9d34a89f992352e1d69418b2db5ed027f8855b95bd +size 2553243008 diff --git a/Hamanasu-Magnum-4B.Q2_K.gguf b/Hamanasu-Magnum-4B.Q2_K.gguf new file mode 100644 index 0000000..d4ebc27 --- /dev/null +++ b/Hamanasu-Magnum-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04c80d750ebc7ca1e24617a052f2edd5bdf393a65a0c15171d8d80e5b7afd70e +size 1839740288 diff --git a/Hamanasu-Magnum-4B.Q3_K_L.gguf b/Hamanasu-Magnum-4B.Q3_K_L.gguf new file mode 100644 index 0000000..0a8f799 --- /dev/null +++ b/Hamanasu-Magnum-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4545e67c98dcb5fe023722c314de30b56d40166aeb1561a07a5452cd145f2e39 +size 2464861568 diff --git a/Hamanasu-Magnum-4B.Q3_K_M.gguf b/Hamanasu-Magnum-4B.Q3_K_M.gguf new file mode 100644 index 0000000..cee7cc0 --- /dev/null +++ b/Hamanasu-Magnum-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66639acc62b77ee412fc8072a0fb185cd30585f85c7196f7560967a647db2560 +size 2296565120 diff --git a/Hamanasu-Magnum-4B.Q3_K_S.gguf b/Hamanasu-Magnum-4B.Q3_K_S.gguf new file mode 100644 index 0000000..b08b51b --- /dev/null +++ b/Hamanasu-Magnum-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:248312f3e073b42cabc2a23c42aef56ef48853bd1231375664a8aaa0ff19ed25 +size 2101529984 diff --git a/Hamanasu-Magnum-4B.Q4_K_M.gguf b/Hamanasu-Magnum-4B.Q4_K_M.gguf new file mode 100644 index 0000000..e20091f --- /dev/null +++ b/Hamanasu-Magnum-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c81ee229e5ab09632b0ffb03427ac558dc982be9b75f46e5092f7d50674a969 +size 2778285440 diff --git a/Hamanasu-Magnum-4B.Q4_K_S.gguf b/Hamanasu-Magnum-4B.Q4_K_S.gguf new file mode 100644 index 0000000..adc22f9 --- /dev/null +++ b/Hamanasu-Magnum-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a60407494cf1aaedbd20292717cbad4f268aee7e8dc46afcf3542af95f91c52 +size 2664252800 diff --git a/Hamanasu-Magnum-4B.Q5_K_M.gguf b/Hamanasu-Magnum-4B.Q5_K_M.gguf new file mode 100644 index 0000000..19f10b5 --- /dev/null +++ b/Hamanasu-Magnum-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf1b6117ebe0785f9918e81e893a591e72571342fccf3c70c5dac712cda1601 +size 3230188928 diff --git a/Hamanasu-Magnum-4B.Q5_K_S.gguf b/Hamanasu-Magnum-4B.Q5_K_S.gguf new file mode 100644 index 0000000..0778259 --- /dev/null +++ b/Hamanasu-Magnum-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c70ef011b786e99a936dc5f1929c1886d6c45313552b10c7e068ba948d29009 +size 3163342208 diff --git a/Hamanasu-Magnum-4B.Q6_K.gguf b/Hamanasu-Magnum-4B.Q6_K.gguf new file mode 100644 index 0000000..677ba5a --- /dev/null +++ b/Hamanasu-Magnum-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e4ea0bf1154d388d7a5b5c18deb65c4fd7b3a04e684073f3c545cdb6cca0ca +size 3710336384 diff --git a/Hamanasu-Magnum-4B.Q8_0.gguf b/Hamanasu-Magnum-4B.Q8_0.gguf new file mode 100644 index 0000000..a45150f --- /dev/null +++ b/Hamanasu-Magnum-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddf0a4aab8e328d42e82fdcdcf49a62433a84f46bf5090471ca1abf9a4560022 +size 4803218816 diff --git a/Hamanasu-Magnum-4B.f16.gguf b/Hamanasu-Magnum-4B.f16.gguf new file mode 100644 index 0000000..727d8f9 --- /dev/null +++ b/Hamanasu-Magnum-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57ed3962e6a988e4c8bd3ea840d42a231c3a34e6e0eaf31a4085a43a900d2190 +size 9033731456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..01667e1 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: Delta-Vector/Hamanasu-Magnum-4B +datasets: +- PocketDoc/Dans-Personamaxx-Logs +- anthracite-org/kalo-opus-instruct-22k-no-refusal +- lodrick-the-lafted/kalo-opus-instruct-3k-filtered +- anthracite-org/nopm_claude_writing_fixed +- anthracite-org/kalo_opus_misc_240827 +- anthracite-org/kalo_misc_part2 +- NewEden/Claude-Instruct-5K +- NewEden/Claude-Instruct-2.7K +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama +- roleplay +- finetune +- storywriting +--- +## About + + + + + + +static quants of https://huggingface.co/Delta-Vector/Hamanasu-Magnum-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hamanasu-Magnum-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-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/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.Q3_K_M.gguf) | Q3_K_M | 2.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.Q3_K_L.gguf) | Q3_K_L | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.IQ4_XS.gguf) | IQ4_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.Q4_K_S.gguf) | Q4_K_S | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.Q4_K_M.gguf) | Q4_K_M | 2.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.Q5_K_S.gguf) | Q5_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.Q6_K.gguf) | Q6_K | 3.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.Q8_0.gguf) | Q8_0 | 4.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-4B-GGUF/resolve/main/Hamanasu-Magnum-4B.f16.gguf) | f16 | 9.1 | 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. + +