commit 3b0499bf7a4764cba6d1b0d999a589be462a3fc3 Author: ModelHub XC Date: Tue Jul 7 11:43:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/heiko-7b-instruct-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cf35a91 --- /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 +heiko-7b-instruct-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +heiko-7b-instruct-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +heiko-7b-instruct-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +heiko-7b-instruct-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +heiko-7b-instruct-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +heiko-7b-instruct-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +heiko-7b-instruct-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +heiko-7b-instruct-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +heiko-7b-instruct-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +heiko-7b-instruct-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +heiko-7b-instruct-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +heiko-7b-instruct-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..37b96ea --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: eriksu/heiko-7b-instruct-v2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/eriksu/heiko-7b-instruct-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#heiko-7b-instruct-v2-GGUF).*** + +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/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/heiko-7b-instruct-v2-GGUF/resolve/main/heiko-7b-instruct-v2.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. + + diff --git a/heiko-7b-instruct-v2.IQ4_XS.gguf b/heiko-7b-instruct-v2.IQ4_XS.gguf new file mode 100644 index 0000000..78981c6 --- /dev/null +++ b/heiko-7b-instruct-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e74bc42ecd6a7208897e8f89ca12c9ef172c04b00b58ffdf9f456e9a36d9125f +size 3944389600 diff --git a/heiko-7b-instruct-v2.Q2_K.gguf b/heiko-7b-instruct-v2.Q2_K.gguf new file mode 100644 index 0000000..f04fb1b --- /dev/null +++ b/heiko-7b-instruct-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:644c670a7e4a86bc0ea92da585f1e2572371f7a5c48112bcfcb22380690d3f97 +size 2719243232 diff --git a/heiko-7b-instruct-v2.Q3_K_L.gguf b/heiko-7b-instruct-v2.Q3_K_L.gguf new file mode 100644 index 0000000..96223bf --- /dev/null +++ b/heiko-7b-instruct-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9742da22ab47ce8cb455c423321967d519c7d85325c1ea4ce64f244b41c1194e +size 3822025696 diff --git a/heiko-7b-instruct-v2.Q3_K_M.gguf b/heiko-7b-instruct-v2.Q3_K_M.gguf new file mode 100644 index 0000000..764d118 --- /dev/null +++ b/heiko-7b-instruct-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285026e498a81e19740d32fde15e845d3a0077d5e68910490059bf7d16f519af +size 3518987232 diff --git a/heiko-7b-instruct-v2.Q3_K_S.gguf b/heiko-7b-instruct-v2.Q3_K_S.gguf new file mode 100644 index 0000000..3d47b90 --- /dev/null +++ b/heiko-7b-instruct-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c68c3e574cd238ad105935556b49ae29e072f43eb94df0c033bb5336d769c0ca +size 3164568544 diff --git a/heiko-7b-instruct-v2.Q4_K_M.gguf b/heiko-7b-instruct-v2.Q4_K_M.gguf new file mode 100644 index 0000000..c934adf --- /dev/null +++ b/heiko-7b-instruct-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dec581aee432f7756840de96fc588d59ea2362768a14a50ee3d8403853400b2e +size 4368440288 diff --git a/heiko-7b-instruct-v2.Q4_K_S.gguf b/heiko-7b-instruct-v2.Q4_K_S.gguf new file mode 100644 index 0000000..9946658 --- /dev/null +++ b/heiko-7b-instruct-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eadba7274759d8d10739f25d5e40d154e7f1c54ee5efc4ffccd3d902a225b005 +size 4140375008 diff --git a/heiko-7b-instruct-v2.Q5_K_M.gguf b/heiko-7b-instruct-v2.Q5_K_M.gguf new file mode 100644 index 0000000..c1cd138 --- /dev/null +++ b/heiko-7b-instruct-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:526ed052baa41b6a05d675f1c7c6bcf257bd39cada064d9b085bd6f8dc024d1e +size 5131410400 diff --git a/heiko-7b-instruct-v2.Q5_K_S.gguf b/heiko-7b-instruct-v2.Q5_K_S.gguf new file mode 100644 index 0000000..894f2d2 --- /dev/null +++ b/heiko-7b-instruct-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5bb4bfbf47f93374f7cab9d153ab41e2b2417d902f094158053c3ba92a558c0 +size 4997716960 diff --git a/heiko-7b-instruct-v2.Q6_K.gguf b/heiko-7b-instruct-v2.Q6_K.gguf new file mode 100644 index 0000000..8ca3246 --- /dev/null +++ b/heiko-7b-instruct-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b72878661d93200ff5f6da07672a667e122a1e6e9947ace58fff247897b8a3cd +size 5942066144 diff --git a/heiko-7b-instruct-v2.Q8_0.gguf b/heiko-7b-instruct-v2.Q8_0.gguf new file mode 100644 index 0000000..2e724d3 --- /dev/null +++ b/heiko-7b-instruct-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f5bf50b8b56e27b18c09cebfc9be76f8804b52a57e81cfbcb4a4c1368c42290 +size 7695858656 diff --git a/heiko-7b-instruct-v2.f16.gguf b/heiko-7b-instruct-v2.f16.gguf new file mode 100644 index 0000000..0a260a5 --- /dev/null +++ b/heiko-7b-instruct-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a6e7a060c1c10408317356faa3a08ccbccee2a79a1b25a47c3eaa53399a143 +size 14484732896