commit 66ede9d0e18b81b9df5c8d228974266abeb23ef0 Author: ModelHub XC Date: Fri Jun 12 01:14:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ZwZ-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6bc561e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +ZwZ-8B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ZwZ-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..61e2c8b --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: inclusionAI/ZwZ-8B +datasets: +- inclusionAI/ZwZ-RL-VQA +- inclusionAI/ZoomBench +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/inclusionAI/ZwZ-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ZwZ-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ZwZ-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/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.mmproj-f16.gguf) | mmproj-f16 | 1.3 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ZwZ-8B-GGUF/resolve/main/ZwZ-8B.f16.gguf) | f16 | 16.5 | 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/ZwZ-8B.IQ4_XS.gguf b/ZwZ-8B.IQ4_XS.gguf new file mode 100644 index 0000000..d6dea05 --- /dev/null +++ b/ZwZ-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33edeb8ea886954821ba118432ee3882d1f3eb2a798e7a2c14186b537066bd6e +size 4593298656 diff --git a/ZwZ-8B.Q2_K.gguf b/ZwZ-8B.Q2_K.gguf new file mode 100644 index 0000000..66c4df2 --- /dev/null +++ b/ZwZ-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2145ac8a7ad54b736000fce5bea8e6a336d96e721b2b6615492877100bf0a6d +size 3281734880 diff --git a/ZwZ-8B.Q3_K_L.gguf b/ZwZ-8B.Q3_K_L.gguf new file mode 100644 index 0000000..546485e --- /dev/null +++ b/ZwZ-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6506636c980b8c5087ec90141616f937278e0163f35b4081076cbef1384b5faf +size 4431396064 diff --git a/ZwZ-8B.Q3_K_M.gguf b/ZwZ-8B.Q3_K_M.gguf new file mode 100644 index 0000000..a69c582 --- /dev/null +++ b/ZwZ-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fcadad73ea4433c0bf10ae567a899861e8bf973cabfd3a6102f46c74068dd77 +size 4124163296 diff --git a/ZwZ-8B.Q3_K_S.gguf b/ZwZ-8B.Q3_K_S.gguf new file mode 100644 index 0000000..ba6d3dc --- /dev/null +++ b/ZwZ-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4dafeed073f4069a3fc6dfc2bfc3e4369d8186512bc956a394d50779938bfae +size 3769613536 diff --git a/ZwZ-8B.Q4_K_M.gguf b/ZwZ-8B.Q4_K_M.gguf new file mode 100644 index 0000000..13ff348 --- /dev/null +++ b/ZwZ-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de77de269b1992c0e9eae9b8eb828a9f35b54aad917a7e381c39af81375442bf +size 5027785952 diff --git a/ZwZ-8B.Q4_K_S.gguf b/ZwZ-8B.Q4_K_S.gguf new file mode 100644 index 0000000..487edd7 --- /dev/null +++ b/ZwZ-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3df0f818ad55429537ab8b7bd37dac8c52344fecd4277c3ee5c1101b5d4270ef +size 4802014432 diff --git a/ZwZ-8B.Q5_K_M.gguf b/ZwZ-8B.Q5_K_M.gguf new file mode 100644 index 0000000..fe11176 --- /dev/null +++ b/ZwZ-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4989ad79a4cfbf7e6baf3fd0a988da596146b407191ea4f1589e59b649f70c6c +size 5851114720 diff --git a/ZwZ-8B.Q5_K_S.gguf b/ZwZ-8B.Q5_K_S.gguf new file mode 100644 index 0000000..25629d0 --- /dev/null +++ b/ZwZ-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ff363d404ca2fd43a0c487ba6707a84db7a49523986530c4b68d2cda4b41ca +size 5720763616 diff --git a/ZwZ-8B.Q6_K.gguf b/ZwZ-8B.Q6_K.gguf new file mode 100644 index 0000000..de2b722 --- /dev/null +++ b/ZwZ-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65eea7f371cf468fff443de9cc2df04cc28132673418d333f94c79f0165929a2 +size 6725901536 diff --git a/ZwZ-8B.Q8_0.gguf b/ZwZ-8B.Q8_0.gguf new file mode 100644 index 0000000..5cb80b7 --- /dev/null +++ b/ZwZ-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f83fa5f672218552f2a3202fd2eeb74040cac4377467fd6beae573f921b579b +size 8709520608 diff --git a/ZwZ-8B.f16.gguf b/ZwZ-8B.f16.gguf new file mode 100644 index 0000000..eaa3884 --- /dev/null +++ b/ZwZ-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04d7a2804372faa2aa7e41527e707aba0e7450bb9f6cafaec825710a181c21b +size 16388046048 diff --git a/ZwZ-8B.mmproj-Q8_0.gguf b/ZwZ-8B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..eead542 --- /dev/null +++ b/ZwZ-8B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb3b99eb41f4608715a6b955bc9079bafcdd50af4a38fcb918f8b0e38c056a0 +size 752290496 diff --git a/ZwZ-8B.mmproj-f16.gguf b/ZwZ-8B.mmproj-f16.gguf new file mode 100644 index 0000000..3b4df62 --- /dev/null +++ b/ZwZ-8B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52853561b1fe3a82007606746190f7900c5860b7ee28fd0cc81a4d7aeb6266b8 +size 1159030592