commit 66e334cc9aa06aff2c9076bc3a9908dbb0b9767f Author: ModelHub XC Date: Mon Apr 27 04:23:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralMonarch-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0783952 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +NeuralMonarch-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMonarch-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralMonarch-7B.IQ4_XS.gguf b/NeuralMonarch-7B.IQ4_XS.gguf new file mode 100644 index 0000000..95a5e72 --- /dev/null +++ b/NeuralMonarch-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baee0b46ee70a9cd8e460a1f14563e60e9b8ae6a9c034ba6595f08ecfdee5d05 +size 3944389824 diff --git a/NeuralMonarch-7B.Q2_K.gguf b/NeuralMonarch-7B.Q2_K.gguf new file mode 100644 index 0000000..97fa3a1 --- /dev/null +++ b/NeuralMonarch-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9908daca21a91ecb83e61e1f7b7f27d8db66b5abfdaf0ae52082f2861603419a +size 2719243456 diff --git a/NeuralMonarch-7B.Q3_K_L.gguf b/NeuralMonarch-7B.Q3_K_L.gguf new file mode 100644 index 0000000..426bad1 --- /dev/null +++ b/NeuralMonarch-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f7a2e364e31d0cb9b0ff53ca00ceb2639e47006792f4df8adc9e7827bf15607 +size 3822025920 diff --git a/NeuralMonarch-7B.Q3_K_M.gguf b/NeuralMonarch-7B.Q3_K_M.gguf new file mode 100644 index 0000000..230b3bc --- /dev/null +++ b/NeuralMonarch-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baba68b3447f8cfe21e4efa8af7af1da256d1ff90d1c44c3370e44ba48e172a9 +size 3518987456 diff --git a/NeuralMonarch-7B.Q3_K_S.gguf b/NeuralMonarch-7B.Q3_K_S.gguf new file mode 100644 index 0000000..61a6f6e --- /dev/null +++ b/NeuralMonarch-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aed7fff98b0d5b4186b034b44f27bfbcdba2e1306801530ab38199d76a898c8d +size 3164568768 diff --git a/NeuralMonarch-7B.Q4_0_4_4.gguf b/NeuralMonarch-7B.Q4_0_4_4.gguf new file mode 100644 index 0000000..1e78950 --- /dev/null +++ b/NeuralMonarch-7B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f36523b1aff02cab9a4205b67d7ceafd8d221bb3e52aafdf48c53caa2169c866 +size 4108917952 diff --git a/NeuralMonarch-7B.Q4_K_M.gguf b/NeuralMonarch-7B.Q4_K_M.gguf new file mode 100644 index 0000000..9d28937 --- /dev/null +++ b/NeuralMonarch-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e677b512212379f9fa0868256af43a05881f61a62038841fdc597acf1a1c922b +size 4368440512 diff --git a/NeuralMonarch-7B.Q4_K_S.gguf b/NeuralMonarch-7B.Q4_K_S.gguf new file mode 100644 index 0000000..7d225dc --- /dev/null +++ b/NeuralMonarch-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56873d3f9b487ce1bb9a72fe229348d00bb2a60b4c454fa28d18278abb08bd9a +size 4140375232 diff --git a/NeuralMonarch-7B.Q5_K_M.gguf b/NeuralMonarch-7B.Q5_K_M.gguf new file mode 100644 index 0000000..fea2594 --- /dev/null +++ b/NeuralMonarch-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5353f6496873510c3ad666b4cba924c1975b99a0934bbb4dd37dfcb557676890 +size 5131410624 diff --git a/NeuralMonarch-7B.Q5_K_S.gguf b/NeuralMonarch-7B.Q5_K_S.gguf new file mode 100644 index 0000000..a867d87 --- /dev/null +++ b/NeuralMonarch-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54075114380086a73e2f2a762cf8d92d9104a95594df2c40e78bf628a30b6f6f +size 4997717184 diff --git a/NeuralMonarch-7B.Q6_K.gguf b/NeuralMonarch-7B.Q6_K.gguf new file mode 100644 index 0000000..506eca3 --- /dev/null +++ b/NeuralMonarch-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f60355741a0268dce4c54b874c3cdc95df2c66af8365ee73cec350fd775b383 +size 5942066368 diff --git a/NeuralMonarch-7B.Q8_0.gguf b/NeuralMonarch-7B.Q8_0.gguf new file mode 100644 index 0000000..af0b55a --- /dev/null +++ b/NeuralMonarch-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:450d497a766793da4734421b4a23495e5dfe2c463c237c006a91cd76b079271e +size 7695858880 diff --git a/NeuralMonarch-7B.f16.gguf b/NeuralMonarch-7B.f16.gguf new file mode 100644 index 0000000..4d3c192 --- /dev/null +++ b/NeuralMonarch-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f84c526bcf92359147a1c4767c5c163dc2f1c91e84d159f261f64125dd60b87 +size 14484733120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f8e7d92 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: mlabonne/NeuralMonarch-7B +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- merge +- lazymergekit +- dpo +- rlhf +--- +## About + + + + + + +static quants of https://huggingface.co/mlabonne/NeuralMonarch-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/NeuralMonarch-7B-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/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralMonarch-7B-GGUF/resolve/main/NeuralMonarch-7B.f16.gguf) | f16 | 14.6 | 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. + +