commit d13f334ab3a9549ca4df2aa9929ae713d1339b71 Author: ModelHub XC Date: Wed Jun 17 20:03:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/koboldai-erebus-extended-32k-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d7ddfb0 --- /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 +koboldai-erebus-extended-32k-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +koboldai-erebus-extended-32k-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ce892fe --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: grimjim/koboldai-erebus-extended-32k-7B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mergekit +- merge +- not-for-all-audiences +--- +## About + + + + + + +static quants of https://huggingface.co/grimjim/koboldai-erebus-extended-32k-7B + + +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/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.IQ3_XS.gguf) | IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/koboldai-erebus-extended-32k-7B-GGUF/resolve/main/koboldai-erebus-extended-32k-7B.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/koboldai-erebus-extended-32k-7B.IQ3_M.gguf b/koboldai-erebus-extended-32k-7B.IQ3_M.gguf new file mode 100644 index 0000000..d3da426 --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c91137aed936ec16fe8b85559ef9314b141e03cba34ca61ffb9884330d01621d +size 3284892416 diff --git a/koboldai-erebus-extended-32k-7B.IQ3_S.gguf b/koboldai-erebus-extended-32k-7B.IQ3_S.gguf new file mode 100644 index 0000000..6be887d --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fca9e67921f9320f7d524187255ae2c2c1aaed25a4792b282fd7523884c6ca8 +size 3182394112 diff --git a/koboldai-erebus-extended-32k-7B.IQ3_XS.gguf b/koboldai-erebus-extended-32k-7B.IQ3_XS.gguf new file mode 100644 index 0000000..ed27ca6 --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4f617420aaff8afe9a2a9fa8c6729915a46d4b8b875923679ceab28c0aba5b0 +size 3018816256 diff --git a/koboldai-erebus-extended-32k-7B.IQ4_XS.gguf b/koboldai-erebus-extended-32k-7B.IQ4_XS.gguf new file mode 100644 index 0000000..a6b4adf --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c8603101d7eaafb9898ba48dcfa974803d22991221a1482b617b045f7a44ad2 +size 3944389376 diff --git a/koboldai-erebus-extended-32k-7B.Q2_K.gguf b/koboldai-erebus-extended-32k-7B.Q2_K.gguf new file mode 100644 index 0000000..0e312e5 --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26980e9b2c00cc8a0ce9297139c0d79642be8bcd421c9afd26c6986aae8fa355 +size 2719243008 diff --git a/koboldai-erebus-extended-32k-7B.Q3_K_L.gguf b/koboldai-erebus-extended-32k-7B.Q3_K_L.gguf new file mode 100644 index 0000000..f35e93b --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4467271ca55cc89cc91f9ec3b35b95f260228b3a5864d8e8f4b5d4c500f3a91 +size 3822025472 diff --git a/koboldai-erebus-extended-32k-7B.Q3_K_M.gguf b/koboldai-erebus-extended-32k-7B.Q3_K_M.gguf new file mode 100644 index 0000000..7d09618 --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ea978ef54a4d8735d202602680218c3ba0f8722bb502ec0fd83ed7b9c52ebbd +size 3518987008 diff --git a/koboldai-erebus-extended-32k-7B.Q3_K_S.gguf b/koboldai-erebus-extended-32k-7B.Q3_K_S.gguf new file mode 100644 index 0000000..4b11402 --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fed3d721dae1655a40e0f7e3be232575cd3e8823cbef1fb458dcee3d0076bbe8 +size 3164568320 diff --git a/koboldai-erebus-extended-32k-7B.Q4_K_M.gguf b/koboldai-erebus-extended-32k-7B.Q4_K_M.gguf new file mode 100644 index 0000000..4cc4e89 --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2e077cb9f093053b92e9e7561b2ae3ff1b9b888801266f0a43639de42fa783 +size 4368440064 diff --git a/koboldai-erebus-extended-32k-7B.Q4_K_S.gguf b/koboldai-erebus-extended-32k-7B.Q4_K_S.gguf new file mode 100644 index 0000000..d51ac7a --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9556ba0df5280f7ac65502ac32895c6784ff1e73751c2f72b855f5eae3e8c71 +size 4140374784 diff --git a/koboldai-erebus-extended-32k-7B.Q5_K_M.gguf b/koboldai-erebus-extended-32k-7B.Q5_K_M.gguf new file mode 100644 index 0000000..1b3cbfd --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adf0c8b17e657c5151a28076b6c09cddb148ce01918e10ce2d6041bfee335be1 +size 5131410176 diff --git a/koboldai-erebus-extended-32k-7B.Q5_K_S.gguf b/koboldai-erebus-extended-32k-7B.Q5_K_S.gguf new file mode 100644 index 0000000..bad1607 --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fc9d16338ba1f4e376f24ed26e19be5b3306acb66cc655835be8e8930f8b576 +size 4997716736 diff --git a/koboldai-erebus-extended-32k-7B.Q6_K.gguf b/koboldai-erebus-extended-32k-7B.Q6_K.gguf new file mode 100644 index 0000000..1401d76 --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af859e71313dfc591d23ffb561530d05d2421db21a4a9f9263d20a916ff2e881 +size 5942065920 diff --git a/koboldai-erebus-extended-32k-7B.Q8_0.gguf b/koboldai-erebus-extended-32k-7B.Q8_0.gguf new file mode 100644 index 0000000..7a468fa --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c32e4e7ee8ae6b2455556a0c24c9aca900c5651368b56f21620d573fa8b779 +size 7695858432 diff --git a/koboldai-erebus-extended-32k-7B.f16.gguf b/koboldai-erebus-extended-32k-7B.f16.gguf new file mode 100644 index 0000000..cdf00ba --- /dev/null +++ b/koboldai-erebus-extended-32k-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9639517a7bf40410b8dfb23aa66478ed2933cac92f28a0ace4c97daf2abfe1d8 +size 14484732672