commit 4f1d0de456031bed10c8d937a09e0aa8686c97d9 Author: ModelHub XC Date: Mon Jul 6 19:42:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Kosmos-Elusive-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f6ace67 --- /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 +Kosmos-Elusive-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kosmos-Elusive-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Kosmos-Elusive-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +Kosmos-Elusive-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Kosmos-Elusive-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Kosmos-Elusive-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kosmos-Elusive-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kosmos-Elusive-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Kosmos-Elusive-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kosmos-Elusive-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kosmos-Elusive-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kosmos-Elusive-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Kosmos-Elusive-8b.IQ4_XS.gguf b/Kosmos-Elusive-8b.IQ4_XS.gguf new file mode 100644 index 0000000..b3976f8 --- /dev/null +++ b/Kosmos-Elusive-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93ee8a5b2b2248e710d44fe578d10234812d54ea2917142eb5413a8b703b5d0c +size 4484363424 diff --git a/Kosmos-Elusive-8b.Q2_K.gguf b/Kosmos-Elusive-8b.Q2_K.gguf new file mode 100644 index 0000000..50ce1b4 --- /dev/null +++ b/Kosmos-Elusive-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f04e0f418bd10fadf3a9a3aafe106aaa156aeff49cfc970fe4efc5370a1d5b +size 3179132064 diff --git a/Kosmos-Elusive-8b.Q3_K_L.gguf b/Kosmos-Elusive-8b.Q3_K_L.gguf new file mode 100644 index 0000000..e7e0f18 --- /dev/null +++ b/Kosmos-Elusive-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b94c9a7493baaddaf4b34989c2d550f520f47caad471f51f306363205cf815 +size 4321957024 diff --git a/Kosmos-Elusive-8b.Q3_K_M.gguf b/Kosmos-Elusive-8b.Q3_K_M.gguf new file mode 100644 index 0000000..3483c26 --- /dev/null +++ b/Kosmos-Elusive-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5243563127e9d574a7b629a6f3653e04c861365f2d84b7116bf050a20b29cbb +size 4018918560 diff --git a/Kosmos-Elusive-8b.Q3_K_S.gguf b/Kosmos-Elusive-8b.Q3_K_S.gguf new file mode 100644 index 0000000..1be4738 --- /dev/null +++ b/Kosmos-Elusive-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2505a8dfeb2e6113ed9fc88b44d1ce886c15c54529cb93409054f4d35dd3db7d +size 3664499872 diff --git a/Kosmos-Elusive-8b.Q4_K_M.gguf b/Kosmos-Elusive-8b.Q4_K_M.gguf new file mode 100644 index 0000000..766333a --- /dev/null +++ b/Kosmos-Elusive-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7255ec9970dd12c33142ba449278cdbf1059254929e318f81f118b64b92d315b +size 4920734880 diff --git a/Kosmos-Elusive-8b.Q4_K_S.gguf b/Kosmos-Elusive-8b.Q4_K_S.gguf new file mode 100644 index 0000000..4cb2f89 --- /dev/null +++ b/Kosmos-Elusive-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec6130b75dc264fc97a4e6b1ddfe1f760f9bee7a01f1e7ce9e21e0db2863ef42 +size 4692669600 diff --git a/Kosmos-Elusive-8b.Q5_K_M.gguf b/Kosmos-Elusive-8b.Q5_K_M.gguf new file mode 100644 index 0000000..e155478 --- /dev/null +++ b/Kosmos-Elusive-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a11c97b4970f839e756605d1be9ee73bd620c6339a07028634edc3fd07a684ff +size 5732988064 diff --git a/Kosmos-Elusive-8b.Q5_K_S.gguf b/Kosmos-Elusive-8b.Q5_K_S.gguf new file mode 100644 index 0000000..3e29da0 --- /dev/null +++ b/Kosmos-Elusive-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:549c110b8567a920038bf9ff820a8341d9434b1b4023f9f40109a9faf2f814dc +size 5599294624 diff --git a/Kosmos-Elusive-8b.Q6_K.gguf b/Kosmos-Elusive-8b.Q6_K.gguf new file mode 100644 index 0000000..1e6fd68 --- /dev/null +++ b/Kosmos-Elusive-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf3d68cbea19b174292738fd7a6df52a5e9354413942fc5701365d2bab5d793a +size 6596007072 diff --git a/Kosmos-Elusive-8b.Q8_0.gguf b/Kosmos-Elusive-8b.Q8_0.gguf new file mode 100644 index 0000000..5f34e90 --- /dev/null +++ b/Kosmos-Elusive-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c09b5a460919364d0529e40e35b3e18df93ae7f21bd1bb85dc3c448094712ade +size 8540771488 diff --git a/Kosmos-Elusive-8b.f16.gguf b/Kosmos-Elusive-8b.f16.gguf new file mode 100644 index 0000000..ce6c601 --- /dev/null +++ b/Kosmos-Elusive-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce26c983b0b3a3ffb81fb337ed61dbbdddeb8bd0ae8748aaffda3222b509db07 +size 16068891808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a816072 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: jaspionjader/Kosmos-Elusive-8b +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/jaspionjader/Kosmos-Elusive-8b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Kosmos-Elusive-8b-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/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Kosmos-Elusive-8b-GGUF/resolve/main/Kosmos-Elusive-8b.f16.gguf) | f16 | 16.2 | 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. + +