commit b3598da43806ebb7f6f0e0d4b479dece6f5d14a1 Author: ModelHub XC Date: Wed Apr 22 19:44:48 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/nekomata-14b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4ebd870 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +nekomata-14b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-14b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..678fbf4 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: rinna/nekomata-14b +datasets: +- mc4 +- wikipedia +- EleutherAI/pile +- oscar-corpus/colossal-oscar-1.0 +- cc100 +language: +- ja +- en +library_name: transformers +license: other +license_link: https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT +license_name: tongyi-qianwen-license-agreement +quantized_by: mradermacher +tags: +- qwen +--- +## About + + + + + + +static quants of https://huggingface.co/rinna/nekomata-14b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/nekomata-14b-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/nekomata-14b-GGUF/resolve/main/nekomata-14b.Q2_K.gguf) | Q2_K | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.IQ3_XS.gguf) | IQ3_XS | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.IQ3_S.gguf) | IQ3_S | 6.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.Q3_K_S.gguf) | Q3_K_S | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.IQ3_M.gguf) | IQ3_M | 7.5 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.Q3_K_M.gguf) | Q3_K_M | 7.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.IQ4_XS.gguf) | IQ4_XS | 8.0 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.Q3_K_L.gguf) | Q3_K_L | 8.1 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.Q4_K_M.gguf) | Q4_K_M | 9.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.Q5_K_S.gguf) | Q5_K_S | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.Q5_K_M.gguf) | Q5_K_M | 11.0 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.Q6_K.gguf) | Q6_K | 12.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/nekomata-14b-GGUF/resolve/main/nekomata-14b.Q8_0.gguf) | Q8_0 | 15.2 | fast, best quality | + +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/nekomata-14b.IQ3_M.gguf b/nekomata-14b.IQ3_M.gguf new file mode 100644 index 0000000..160beb3 --- /dev/null +++ b/nekomata-14b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3e9bfd8ac8ec76e7d585fdcf05900103610f44c158615fb5a2d94cf9ace2c3 +size 7374676096 diff --git a/nekomata-14b.IQ3_S.gguf b/nekomata-14b.IQ3_S.gguf new file mode 100644 index 0000000..08a25ea --- /dev/null +++ b/nekomata-14b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:858534906a47c8e9d1231c495c785f4c13d3312bdfdd9daf559ae391c87d37f3 +size 6773792896 diff --git a/nekomata-14b.IQ3_XS.gguf b/nekomata-14b.IQ3_XS.gguf new file mode 100644 index 0000000..ae581e1 --- /dev/null +++ b/nekomata-14b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d61c62068329a79d559a9b9f1338e5552bbb8d1ab86bc30b1a51dc4687224a2 +size 6576570496 diff --git a/nekomata-14b.IQ4_XS.gguf b/nekomata-14b.IQ4_XS.gguf new file mode 100644 index 0000000..6fd13a2 --- /dev/null +++ b/nekomata-14b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294c632aecc7918822eaa4b31404c8985ff2caa7c1efa04ca0c9ce0793cb960d +size 7914344576 diff --git a/nekomata-14b.Q2_K.gguf b/nekomata-14b.Q2_K.gguf new file mode 100644 index 0000000..a1a519f --- /dev/null +++ b/nekomata-14b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee3e761ec0e2f73a14877ba0e08a0abf6d8feed60f8dd74cf3494c31bac2681a +size 5805478016 diff --git a/nekomata-14b.Q3_K_L.gguf b/nekomata-14b.Q3_K_L.gguf new file mode 100644 index 0000000..d0e40b3 --- /dev/null +++ b/nekomata-14b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48bbd750bbe31cf2839246099163bc99cf832ba7e852b593bbb6379bf2390ce7 +size 7987847296 diff --git a/nekomata-14b.Q3_K_M.gguf b/nekomata-14b.Q3_K_M.gguf new file mode 100644 index 0000000..120b999 --- /dev/null +++ b/nekomata-14b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88a8895137816bca387514989ec0a0e5ab559f9a8a4b7058c02bb2c6333327b9 +size 7690231936 diff --git a/nekomata-14b.Q3_K_S.gguf b/nekomata-14b.Q3_K_S.gguf new file mode 100644 index 0000000..c40dd71 --- /dev/null +++ b/nekomata-14b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8842583faa7ed0895786cad03dfcaf8b32a7192f48df8e10bd06beb6bf9b66c2 +size 6773792896 diff --git a/nekomata-14b.Q4_K_M.gguf b/nekomata-14b.Q4_K_M.gguf new file mode 100644 index 0000000..b498b86 --- /dev/null +++ b/nekomata-14b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8951049a80ddcffc47bf4ffbd0c266489368ce51c149a5c0cbb76929adbf35dd +size 9449074816 diff --git a/nekomata-14b.Q4_K_S.gguf b/nekomata-14b.Q4_K_S.gguf new file mode 100644 index 0000000..bc574f2 --- /dev/null +++ b/nekomata-14b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96ddfa368e5c48dd3d17e295639b2a67dd9e0b2acc2478987f9c95c3d123c027 +size 8551846016 diff --git a/nekomata-14b.Q5_K_M.gguf b/nekomata-14b.Q5_K_M.gguf new file mode 100644 index 0000000..03fdc0a --- /dev/null +++ b/nekomata-14b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125e2955e0ffb2d16e3c1d8947ac895ae0a1cfc39cb8f71ac3e868da355961c7 +size 10884149376 diff --git a/nekomata-14b.Q5_K_S.gguf b/nekomata-14b.Q5_K_S.gguf new file mode 100644 index 0000000..a4324d1 --- /dev/null +++ b/nekomata-14b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4025340849f6b8321c18e687db3fbe39ad8293c689afcddeaddd8d0e6eae3e9 +size 10028085376 diff --git a/nekomata-14b.Q6_K.gguf b/nekomata-14b.Q6_K.gguf new file mode 100644 index 0000000..36ef217 --- /dev/null +++ b/nekomata-14b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc247f20b416d2b1195fa801b19c6ac2249801e9d04ea312f2666d8570513a36 +size 12310151296 diff --git a/nekomata-14b.Q8_0.gguf b/nekomata-14b.Q8_0.gguf new file mode 100644 index 0000000..59bfcab --- /dev/null +++ b/nekomata-14b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:516dc8272bae28c48488370241892ca81a530179f725aad036bc3035fcf5a4d5 +size 15061721216