commit 6ca4e64969b6b7030a8a563a0cbe715034ff84e7 Author: ModelHub XC Date: Sun Oct 11 19:07:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/InnerILLM-7B-slerp-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f15a181 --- /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 +InnerILLM-7B-slerp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InnerILLM-7B-slerp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +InnerILLM-7B-slerp.f16.gguf filter=lfs diff=lfs merge=lfs -text +InnerILLM-7B-slerp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InnerILLM-7B-slerp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +InnerILLM-7B-slerp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InnerILLM-7B-slerp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InnerILLM-7B-slerp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +InnerILLM-7B-slerp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InnerILLM-7B-slerp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InnerILLM-7B-slerp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InnerILLM-7B-slerp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/InnerILLM-7B-slerp.IQ4_XS.gguf b/InnerILLM-7B-slerp.IQ4_XS.gguf new file mode 100644 index 0000000..00bbd2e --- /dev/null +++ b/InnerILLM-7B-slerp.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea60774f21563e1d6fc5ff4a4d8158b147e95c541f1c73599eabc3231aeaff48 +size 3944389888 diff --git a/InnerILLM-7B-slerp.Q2_K.gguf b/InnerILLM-7B-slerp.Q2_K.gguf new file mode 100644 index 0000000..89e08a6 --- /dev/null +++ b/InnerILLM-7B-slerp.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f987596fa9ce5cc44de01d9554abd6508d84577e52f031aef8cd31cb074ddc0 +size 2719243520 diff --git a/InnerILLM-7B-slerp.Q3_K_L.gguf b/InnerILLM-7B-slerp.Q3_K_L.gguf new file mode 100644 index 0000000..5fe9d2b --- /dev/null +++ b/InnerILLM-7B-slerp.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1a47b9cb544b812eb6b41ee43c2388768b1b728fb483732053f1b9f7d1a28aa +size 3822025984 diff --git a/InnerILLM-7B-slerp.Q3_K_M.gguf b/InnerILLM-7B-slerp.Q3_K_M.gguf new file mode 100644 index 0000000..5492d48 --- /dev/null +++ b/InnerILLM-7B-slerp.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ea4e3fe9dd0b441eb30a09fe65d0fe52d75a6ac1c66e371ddf598ab08b3797f +size 3518987520 diff --git a/InnerILLM-7B-slerp.Q3_K_S.gguf b/InnerILLM-7B-slerp.Q3_K_S.gguf new file mode 100644 index 0000000..d0d85e9 --- /dev/null +++ b/InnerILLM-7B-slerp.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02cb08e71701b04c1bd47dc051c28967bb0d4429fedcb2d3540b0b141858b310 +size 3164568832 diff --git a/InnerILLM-7B-slerp.Q4_K_M.gguf b/InnerILLM-7B-slerp.Q4_K_M.gguf new file mode 100644 index 0000000..cd9ddef --- /dev/null +++ b/InnerILLM-7B-slerp.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4accf00ddd8d730b706b6cb73bace4482756da1460b60fd05d7d437e583a4d40 +size 4368440576 diff --git a/InnerILLM-7B-slerp.Q4_K_S.gguf b/InnerILLM-7B-slerp.Q4_K_S.gguf new file mode 100644 index 0000000..aa850c1 --- /dev/null +++ b/InnerILLM-7B-slerp.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3488f86b0f41a44ade7b590612563f44b590fbe2e4a9bf765e068472cde0664d +size 4140375296 diff --git a/InnerILLM-7B-slerp.Q5_K_M.gguf b/InnerILLM-7B-slerp.Q5_K_M.gguf new file mode 100644 index 0000000..69a9f97 --- /dev/null +++ b/InnerILLM-7B-slerp.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8543f201d374c7d628f2b3b3c7367c8a48559aef37244df286f81286c619e943 +size 5131410688 diff --git a/InnerILLM-7B-slerp.Q5_K_S.gguf b/InnerILLM-7B-slerp.Q5_K_S.gguf new file mode 100644 index 0000000..ac17dea --- /dev/null +++ b/InnerILLM-7B-slerp.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0230efea2f8b2d67f56d2e8de3bc2d05ecff5c5969c5e5372b04ae38aefcec7b +size 4997717248 diff --git a/InnerILLM-7B-slerp.Q6_K.gguf b/InnerILLM-7B-slerp.Q6_K.gguf new file mode 100644 index 0000000..45826f4 --- /dev/null +++ b/InnerILLM-7B-slerp.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:147002210b511fef0523dc8371be1884dd3e9608fc5a7ea8afd8576a1d377e20 +size 5942066432 diff --git a/InnerILLM-7B-slerp.Q8_0.gguf b/InnerILLM-7B-slerp.Q8_0.gguf new file mode 100644 index 0000000..6dfe22c --- /dev/null +++ b/InnerILLM-7B-slerp.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad5b8e983dd3dcad21add958e12d54ee7c3137e94ffd78e0802222fd4bc19655 +size 7695858944 diff --git a/InnerILLM-7B-slerp.f16.gguf b/InnerILLM-7B-slerp.f16.gguf new file mode 100644 index 0000000..f303374 --- /dev/null +++ b/InnerILLM-7B-slerp.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e4f884ffb32691ee831342941e8cfe194734c07d8bbedce5b069952d6a43e0 +size 14484733184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..163956e --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: InnerI/InnerILLM-7B-slerp +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- OpenPipe/mistral-ft-optimized-1218 +- mlabonne/NeuralHermes-2.5-Mistral-7B +--- +## About + + + + + + +static quants of https://huggingface.co/InnerI/InnerILLM-7B-slerp + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/InnerILLM-7B-slerp-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/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/InnerILLM-7B-slerp-GGUF/resolve/main/InnerILLM-7B-slerp.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +