commit 9d848686d138dc245fb4afd0e29e624e4f2e87f6 Author: ModelHub XC Date: Sat May 9 21:21:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralMerge-9B-Ties-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1a506cc --- /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 +NeuralMerge-9B-Ties.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMerge-9B-Ties.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMerge-9B-Ties.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMerge-9B-Ties.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMerge-9B-Ties.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMerge-9B-Ties.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMerge-9B-Ties.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMerge-9B-Ties.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMerge-9B-Ties.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMerge-9B-Ties.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMerge-9B-Ties.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMerge-9B-Ties.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralMerge-9B-Ties.IQ4_XS.gguf b/NeuralMerge-9B-Ties.IQ4_XS.gguf new file mode 100644 index 0000000..8b5c8b6 --- /dev/null +++ b/NeuralMerge-9B-Ties.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af61d41ff81bb90075e57db5110bf79d42d1f35646b9a0e56051cc952fb7dc9c +size 3944389984 diff --git a/NeuralMerge-9B-Ties.Q2_K.gguf b/NeuralMerge-9B-Ties.Q2_K.gguf new file mode 100644 index 0000000..3ef1d67 --- /dev/null +++ b/NeuralMerge-9B-Ties.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7364ee20dee6550171e8af627be384b6d0a6d90b03a1935c735e68c735502d35 +size 2719243616 diff --git a/NeuralMerge-9B-Ties.Q3_K_L.gguf b/NeuralMerge-9B-Ties.Q3_K_L.gguf new file mode 100644 index 0000000..6831999 --- /dev/null +++ b/NeuralMerge-9B-Ties.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61a86f4f1fb32f07cd3e7c7941f052d428712d8175670ff20556f0f00b252f9 +size 3822026080 diff --git a/NeuralMerge-9B-Ties.Q3_K_M.gguf b/NeuralMerge-9B-Ties.Q3_K_M.gguf new file mode 100644 index 0000000..15d73f1 --- /dev/null +++ b/NeuralMerge-9B-Ties.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e3567bb6999c353d0071828129353b6c90803860adb8c71b0ba3312610a934a +size 3518987616 diff --git a/NeuralMerge-9B-Ties.Q3_K_S.gguf b/NeuralMerge-9B-Ties.Q3_K_S.gguf new file mode 100644 index 0000000..77316f3 --- /dev/null +++ b/NeuralMerge-9B-Ties.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:939654c190e45dd48df800bae8f432c2d772a65cfdc9d231189ad1a91002b934 +size 3164568928 diff --git a/NeuralMerge-9B-Ties.Q4_K_M.gguf b/NeuralMerge-9B-Ties.Q4_K_M.gguf new file mode 100644 index 0000000..b85bed1 --- /dev/null +++ b/NeuralMerge-9B-Ties.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac356c5c8497b10f08fe22a2734cef97c75e0b46d5988193827b43e133d15eda +size 4368440672 diff --git a/NeuralMerge-9B-Ties.Q4_K_S.gguf b/NeuralMerge-9B-Ties.Q4_K_S.gguf new file mode 100644 index 0000000..f2a5a31 --- /dev/null +++ b/NeuralMerge-9B-Ties.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:357f205a816c7deb9f7afaaea5892d55ff9ad94054bdb218d4b2df890f75dd4f +size 4140375392 diff --git a/NeuralMerge-9B-Ties.Q5_K_M.gguf b/NeuralMerge-9B-Ties.Q5_K_M.gguf new file mode 100644 index 0000000..ad68cf2 --- /dev/null +++ b/NeuralMerge-9B-Ties.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a29ece579b214b27ea30114be18b840bc7f755ea078f423e6ee961c8aa6710 +size 5131410784 diff --git a/NeuralMerge-9B-Ties.Q5_K_S.gguf b/NeuralMerge-9B-Ties.Q5_K_S.gguf new file mode 100644 index 0000000..9714d37 --- /dev/null +++ b/NeuralMerge-9B-Ties.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df02d61bf72dc6b8dfb3be143131ff0a4aae1233c6981ccd0763f9f91a0df890 +size 4997717344 diff --git a/NeuralMerge-9B-Ties.Q6_K.gguf b/NeuralMerge-9B-Ties.Q6_K.gguf new file mode 100644 index 0000000..f869615 --- /dev/null +++ b/NeuralMerge-9B-Ties.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c30b05934a5e9cff0dfa0505381ea2e64922b40a34ce5d23a14d94e225adb1d7 +size 5942066528 diff --git a/NeuralMerge-9B-Ties.Q8_0.gguf b/NeuralMerge-9B-Ties.Q8_0.gguf new file mode 100644 index 0000000..b011141 --- /dev/null +++ b/NeuralMerge-9B-Ties.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f363901daf5d72186ace38335461426a5965e06aeee23813e56ffa44156c4c7 +size 7695859040 diff --git a/NeuralMerge-9B-Ties.f16.gguf b/NeuralMerge-9B-Ties.f16.gguf new file mode 100644 index 0000000..14fa121 --- /dev/null +++ b/NeuralMerge-9B-Ties.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23f37e8c3081dfb4b3fe978dfabf4c34b41760e2d944f63e7b828de6f88be021 +size 14484733280 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2f9bf12 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: ntegrals/NeuralMerge-9B-Ties +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ntegrals/NeuralMerge-9B-Ties + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NeuralMerge-9B-Ties-GGUF).*** + +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/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralMerge-9B-Ties-GGUF/resolve/main/NeuralMerge-9B-Ties.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. + +