commit 4e3e870602a8306b20f8a05ef7396786b50a1739 Author: ModelHub XC Date: Fri Jun 19 03:14:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/nekomata-7b-instruction-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1a86cd6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-7b-instruction.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.f16.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +nekomata-7b-instruction.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..45f9d64 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: rinna/nekomata-7b-instruction +datasets: +- databricks/databricks-dolly-15k +- kunishou/databricks-dolly-15k-ja +- izumi-lab/llm-japanese-dataset +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-7b-instruction + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/nekomata-7b-instruction-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-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.IQ3_S.gguf) | IQ3_S | 3.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.IQ3_M.gguf) | IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.Q5_K_S.gguf) | Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.Q8_0.gguf) | Q8_0 | 8.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/nekomata-7b-instruction-GGUF/resolve/main/nekomata-7b-instruction.f16.gguf) | f16 | 15.5 | 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. + + diff --git a/nekomata-7b-instruction.IQ3_M.gguf b/nekomata-7b-instruction.IQ3_M.gguf new file mode 100644 index 0000000..fddf280 --- /dev/null +++ b/nekomata-7b-instruction.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a479793a3ee84866193ff3a822f24c13c2db74cb56819f3f731c26873ab2f26f +size 3878319776 diff --git a/nekomata-7b-instruction.IQ3_S.gguf b/nekomata-7b-instruction.IQ3_S.gguf new file mode 100644 index 0000000..8525dd0 --- /dev/null +++ b/nekomata-7b-instruction.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db571d9fbcf3f2757b4013c5ea77e3cd57927afd144505a419b28d03fe5d095 +size 3569153696 diff --git a/nekomata-7b-instruction.IQ3_XS.gguf b/nekomata-7b-instruction.IQ3_XS.gguf new file mode 100644 index 0000000..773e912 --- /dev/null +++ b/nekomata-7b-instruction.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60bd1cb4b1f0f73227648a7a8c124b9b9e4c3b2e685f3f4ba852ba5cd0b41da0 +size 3467703968 diff --git a/nekomata-7b-instruction.IQ4_XS.gguf b/nekomata-7b-instruction.IQ4_XS.gguf new file mode 100644 index 0000000..f493674 --- /dev/null +++ b/nekomata-7b-instruction.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e013fa7fbb374a5f5068a18ea87a080693fc584fb0ed8c20a61cf0625c477f61 +size 4318258848 diff --git a/nekomata-7b-instruction.Q2_K.gguf b/nekomata-7b-instruction.Q2_K.gguf new file mode 100644 index 0000000..a5bd57c --- /dev/null +++ b/nekomata-7b-instruction.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61b737caccb21dfb87a41fd06911f1f6d6a4e4bb0ee23cd6a78956a7ed89a67 +size 3049293472 diff --git a/nekomata-7b-instruction.Q3_K_L.gguf b/nekomata-7b-instruction.Q3_K_L.gguf new file mode 100644 index 0000000..cf12015 --- /dev/null +++ b/nekomata-7b-instruction.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21ba7887bfc905c016cb3dae11e7771a0fc27b1c278f223422d5679a6f4bfd51 +size 4293457568 diff --git a/nekomata-7b-instruction.Q3_K_M.gguf b/nekomata-7b-instruction.Q3_K_M.gguf new file mode 100644 index 0000000..c6a1a0f --- /dev/null +++ b/nekomata-7b-instruction.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9071aad0d867979108e35a04c8abf979bc82d153b4cd4907b0db22cbfc819cc4 +size 4057265824 diff --git a/nekomata-7b-instruction.Q3_K_S.gguf b/nekomata-7b-instruction.Q3_K_S.gguf new file mode 100644 index 0000000..4b87407 --- /dev/null +++ b/nekomata-7b-instruction.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b9c2698412d457054a4754c5d4c2b5666eb3448ff57e6f2a997f268ab1f5c9 +size 3569153696 diff --git a/nekomata-7b-instruction.Q4_K_M.gguf b/nekomata-7b-instruction.Q4_K_M.gguf new file mode 100644 index 0000000..a4325e7 --- /dev/null +++ b/nekomata-7b-instruction.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2c55e8bf32638604d7f58def87c93bb260505bda4dd2717f95fe2516374424b +size 4899219104 diff --git a/nekomata-7b-instruction.Q4_K_S.gguf b/nekomata-7b-instruction.Q4_K_S.gguf new file mode 100644 index 0000000..914c582 --- /dev/null +++ b/nekomata-7b-instruction.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67dc6b435f129faea0aab2379c58dcd3f05284f46c05ea90e8860eed68851116 +size 4534445728 diff --git a/nekomata-7b-instruction.Q5_K_M.gguf b/nekomata-7b-instruction.Q5_K_M.gguf new file mode 100644 index 0000000..c01c67a --- /dev/null +++ b/nekomata-7b-instruction.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b497fb525f02772f9c881e48a126e6c0168152e5f552874eb72943fb478069 +size 5708916384 diff --git a/nekomata-7b-instruction.Q5_K_S.gguf b/nekomata-7b-instruction.Q5_K_S.gguf new file mode 100644 index 0000000..f54c697 --- /dev/null +++ b/nekomata-7b-instruction.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72e2201e88187372bbfc76e73fe916fd3c63c6e86aaf093bd0f6edc178006c22 +size 5399193248 diff --git a/nekomata-7b-instruction.Q6_K.gguf b/nekomata-7b-instruction.Q6_K.gguf new file mode 100644 index 0000000..a9771bf --- /dev/null +++ b/nekomata-7b-instruction.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03cd947408cd8f927a7a5248c206fbab88526dbef1f84103af99f9a6fb13a83d +size 6341940896 diff --git a/nekomata-7b-instruction.Q8_0.gguf b/nekomata-7b-instruction.Q8_0.gguf new file mode 100644 index 0000000..8a671b4 --- /dev/null +++ b/nekomata-7b-instruction.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89b1e191de93233aacc892cda59608fe4689f80cbee4e05adf7c30094b082c6b +size 8211789472 diff --git a/nekomata-7b-instruction.f16.gguf b/nekomata-7b-instruction.f16.gguf new file mode 100644 index 0000000..1f357b4 --- /dev/null +++ b/nekomata-7b-instruction.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076dfc52da33c8cde35a86db641cf10a8b12f4c5d7d36282c6aa9f8477137582 +size 15449912992