commit 6355f04b98224064372bef5151cee382e00fb5df Author: ModelHub XC Date: Fri Jun 12 01:20:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/InnoSpark-7B-0715-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8321a7e --- /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 +InnoSpark-7B-0715.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InnoSpark-7B-0715.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +InnoSpark-7B-0715.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InnoSpark-7B-0715.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +InnoSpark-7B-0715.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InnoSpark-7B-0715.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InnoSpark-7B-0715.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +InnoSpark-7B-0715.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InnoSpark-7B-0715.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InnoSpark-7B-0715.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InnoSpark-7B-0715.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +InnoSpark-7B-0715.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/InnoSpark-7B-0715.IQ4_XS.gguf b/InnoSpark-7B-0715.IQ4_XS.gguf new file mode 100644 index 0000000..870c9fd --- /dev/null +++ b/InnoSpark-7B-0715.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a953f9ecbca2f75b495b0fbe091de4b73150b5b539b82e076cd7831be6bea9da +size 4250298944 diff --git a/InnoSpark-7B-0715.Q2_K.gguf b/InnoSpark-7B-0715.Q2_K.gguf new file mode 100644 index 0000000..2604d78 --- /dev/null +++ b/InnoSpark-7B-0715.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:933653eff36e7c3bbc657fec2fe42b546004721e2cc269fed714db100bde00cc +size 3015940672 diff --git a/InnoSpark-7B-0715.Q3_K_L.gguf b/InnoSpark-7B-0715.Q3_K_L.gguf new file mode 100644 index 0000000..18ed8c3 --- /dev/null +++ b/InnoSpark-7B-0715.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08ff2ea4bcea3f6f1660bccbb53640e546ae665a22ae9fe09df2630e85c03fb +size 4088459840 diff --git a/InnoSpark-7B-0715.Q3_K_M.gguf b/InnoSpark-7B-0715.Q3_K_M.gguf new file mode 100644 index 0000000..0bc8581 --- /dev/null +++ b/InnoSpark-7B-0715.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5430e16f521fe1707eea9934ce57c128b2179c66d4f0110e134809d25704585a +size 3808391744 diff --git a/InnoSpark-7B-0715.Q3_K_S.gguf b/InnoSpark-7B-0715.Q3_K_S.gguf new file mode 100644 index 0000000..07f78a4 --- /dev/null +++ b/InnoSpark-7B-0715.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fcec8bd031e3914833fa53be8a97cf252f4f2eb552ae125de6289d484cac261 +size 3492368960 diff --git a/InnoSpark-7B-0715.Q4_K_M.gguf b/InnoSpark-7B-0715.Q4_K_M.gguf new file mode 100644 index 0000000..419ac87 --- /dev/null +++ b/InnoSpark-7B-0715.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b58e7cd23032ff546b66b2234fca3cb6d850fd4900359fe923ac52df4bb66ae +size 4683074112 diff --git a/InnoSpark-7B-0715.Q4_K_S.gguf b/InnoSpark-7B-0715.Q4_K_S.gguf new file mode 100644 index 0000000..e61a383 --- /dev/null +++ b/InnoSpark-7B-0715.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f05af93b6441297fc1d0246cce12cac50b1b2aa3a846fb08f2d544a5545d2527 +size 4457769536 diff --git a/InnoSpark-7B-0715.Q5_K_M.gguf b/InnoSpark-7B-0715.Q5_K_M.gguf new file mode 100644 index 0000000..29286f9 --- /dev/null +++ b/InnoSpark-7B-0715.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c83d6ec5c0535d802ac86cbdbf74bd0c8f9168778c5e69665529489b93681eb0 +size 5444831808 diff --git a/InnoSpark-7B-0715.Q5_K_S.gguf b/InnoSpark-7B-0715.Q5_K_S.gguf new file mode 100644 index 0000000..84f03dd --- /dev/null +++ b/InnoSpark-7B-0715.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e83014e89f433535c43973c1bb5f460feec5d08bd9ffa7ba475aac3862ee7117 +size 5315177024 diff --git a/InnoSpark-7B-0715.Q6_K.gguf b/InnoSpark-7B-0715.Q6_K.gguf new file mode 100644 index 0000000..de7c255 --- /dev/null +++ b/InnoSpark-7B-0715.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efe2a1aac3b7053ec19583bedf32fe1c274161473d6a0f7bc6613ca0c84dedd2 +size 6254199360 diff --git a/InnoSpark-7B-0715.Q8_0.gguf b/InnoSpark-7B-0715.Q8_0.gguf new file mode 100644 index 0000000..f2351b8 --- /dev/null +++ b/InnoSpark-7B-0715.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c168bbbbbe07ca6aa68ba5255115d95a699d741cb9d4573b6789a712d30096 +size 8098525760 diff --git a/InnoSpark-7B-0715.f16.gguf b/InnoSpark-7B-0715.f16.gguf new file mode 100644 index 0000000..be0a41a --- /dev/null +++ b/InnoSpark-7B-0715.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba7401f4ddd0003940a61cd56b1f2e1d13e583507be3092866ec100ab125b3c +size 15237853760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3078a33 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: sii-research/InnoSpark-7B-0715 +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/sii-research/InnoSpark-7B-0715 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InnoSpark-7B-0715-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/InnoSpark-7B-0715-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/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/InnoSpark-7B-0715-GGUF/resolve/main/InnoSpark-7B-0715.f16.gguf) | f16 | 15.3 | 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. + +