commit 0bbe06af724759302a97c4dd87989bbca1faf0a7 Author: ModelHub XC Date: Thu Jun 4 16:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/nemophi-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..140ba00 --- /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 +nemophi.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +nemophi.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +nemophi.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nemophi.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nemophi.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nemophi.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nemophi.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nemophi.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nemophi.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nemophi.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +nemophi.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nemophi.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c14b843 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: pavan1249/nemophi +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/pavan1249/nemophi + + +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/nemophi-GGUF/resolve/main/nemophi.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/nemophi-GGUF/resolve/main/nemophi.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/nemophi-GGUF/resolve/main/nemophi.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/nemophi-GGUF/resolve/main/nemophi.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/nemophi-GGUF/resolve/main/nemophi.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/nemophi-GGUF/resolve/main/nemophi.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nemophi-GGUF/resolve/main/nemophi.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nemophi-GGUF/resolve/main/nemophi.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/nemophi-GGUF/resolve/main/nemophi.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/nemophi-GGUF/resolve/main/nemophi.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/nemophi-GGUF/resolve/main/nemophi.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/nemophi-GGUF/resolve/main/nemophi.f16.gguf) | f16 | 7.7 | 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/nemophi.IQ4_XS.gguf b/nemophi.IQ4_XS.gguf new file mode 100644 index 0000000..1476444 --- /dev/null +++ b/nemophi.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba0281440771963ba0cd88c2ff37255946a7c4e3afd74162a93348771cab7a27 +size 2075580864 diff --git a/nemophi.Q2_K.gguf b/nemophi.Q2_K.gguf new file mode 100644 index 0000000..5005da4 --- /dev/null +++ b/nemophi.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466b589ee303add899a40b12442948daaca6680cacc118e19baf40a7b638f4c7 +size 1416203712 diff --git a/nemophi.Q3_K_L.gguf b/nemophi.Q3_K_L.gguf new file mode 100644 index 0000000..1badc6b --- /dev/null +++ b/nemophi.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cca9d6ecb2d1afd2a539df657f2ad6f31c6d9f5b56833d2e685f2c9c5c60f82 +size 2087596992 diff --git a/nemophi.Q3_K_M.gguf b/nemophi.Q3_K_M.gguf new file mode 100644 index 0000000..c179ab4 --- /dev/null +++ b/nemophi.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7e31aff2e14ece4e4ff309aadb72f4ebe9ca0a2cce03db2c4e432621ccd96af +size 1955476416 diff --git a/nemophi.Q3_K_S.gguf b/nemophi.Q3_K_S.gguf new file mode 100644 index 0000000..2e9bb74 --- /dev/null +++ b/nemophi.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f430ffc474572600cd15862780d67d28fa98be2a9cdb6cb7a76b0d0aed35b80a +size 1681798080 diff --git a/nemophi.Q4_K_M.gguf b/nemophi.Q4_K_M.gguf new file mode 100644 index 0000000..c67364b --- /dev/null +++ b/nemophi.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7059700400e2ae6bff0550629a8488af72fac988d0dc0fb25aaced7f2f6e8a26 +size 2393231808 diff --git a/nemophi.Q4_K_S.gguf b/nemophi.Q4_K_S.gguf new file mode 100644 index 0000000..2572644 --- /dev/null +++ b/nemophi.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41f0f86f1492624fd315b1c83d83a6b4c478c1c68169fb386c6ba753dc78f59e +size 2188759488 diff --git a/nemophi.Q5_K_M.gguf b/nemophi.Q5_K_M.gguf new file mode 100644 index 0000000..1a1158c --- /dev/null +++ b/nemophi.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfb4b6fed9f5d0c36a4bd8c60e7e26cd0cbe91b6fc6a59039537392d04242430 +size 2815275456 diff --git a/nemophi.Q5_K_S.gguf b/nemophi.Q5_K_S.gguf new file mode 100644 index 0000000..50ddd5a --- /dev/null +++ b/nemophi.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a1133ae92abb33d7cea86cbd594c6df83a3c0e84d9991343528d5d852c637ad +size 2641473984 diff --git a/nemophi.Q6_K.gguf b/nemophi.Q6_K.gguf new file mode 100644 index 0000000..629aa64 --- /dev/null +++ b/nemophi.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03aa81cdbd5a3506bfb15cf7fad728a77ef8b5d86586380cca82767274f7bafc +size 3135852480 diff --git a/nemophi.Q8_0.gguf b/nemophi.Q8_0.gguf new file mode 100644 index 0000000..2b6b827 --- /dev/null +++ b/nemophi.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a38f9acf36ae9db0a8467e72fe47b5f403aba17a4679165b93199b654ab06dee +size 4061221824 diff --git a/nemophi.f16.gguf b/nemophi.f16.gguf new file mode 100644 index 0000000..d4d7eec --- /dev/null +++ b/nemophi.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b66d270e01b73a2a7611dbc0f7b900113e362e859e089eec1dcd10535813b41 +size 7643296704