commit 2ff170324893b93f403cdd678d2f2debfe1905e2 Author: ModelHub XC Date: Wed Jun 10 08:58:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GLM4-9B-Neon-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6897000 --- /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 +GLM4-9B-Neon-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GLM4-9B-Neon-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GLM4-9B-Neon-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GLM4-9B-Neon-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GLM4-9B-Neon-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM4-9B-Neon-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GLM4-9B-Neon-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GLM4-9B-Neon-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM4-9B-Neon-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GLM4-9B-Neon-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM4-9B-Neon-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GLM4-9B-Neon-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GLM4-9B-Neon-v2.IQ4_XS.gguf b/GLM4-9B-Neon-v2.IQ4_XS.gguf new file mode 100644 index 0000000..cb02eaa --- /dev/null +++ b/GLM4-9B-Neon-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a6d7dd7bb09ea74e1d84845636d938751c373555e3ef82cc61260fe842021de +size 5314869824 diff --git a/GLM4-9B-Neon-v2.Q2_K.gguf b/GLM4-9B-Neon-v2.Q2_K.gguf new file mode 100644 index 0000000..ce848f7 --- /dev/null +++ b/GLM4-9B-Neon-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:291959af9e0585a8084c7d8fc7baad8951af7d303ad9c80e39849f372dab6ed0 +size 4006345280 diff --git a/GLM4-9B-Neon-v2.Q3_K_L.gguf b/GLM4-9B-Neon-v2.Q3_K_L.gguf new file mode 100644 index 0000000..2604378 --- /dev/null +++ b/GLM4-9B-Neon-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3033c725c67efce1aabb125e1a8ae9eeb753dbd0e7a37097800558f3ae6a504b +size 5196610112 diff --git a/GLM4-9B-Neon-v2.Q3_K_M.gguf b/GLM4-9B-Neon-v2.Q3_K_M.gguf new file mode 100644 index 0000000..bbc03e6 --- /dev/null +++ b/GLM4-9B-Neon-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6ca7ef132e5489d15e44957d96adb9649c0cbaa8d47643d5842dce908a6c22 +size 4974508608 diff --git a/GLM4-9B-Neon-v2.Q3_K_S.gguf b/GLM4-9B-Neon-v2.Q3_K_S.gguf new file mode 100644 index 0000000..5c7411b --- /dev/null +++ b/GLM4-9B-Neon-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65b0753180309be2edc6334c11883f8654e1f9960d87ae0b7b0f1e04e44d7e1a +size 4592040512 diff --git a/GLM4-9B-Neon-v2.Q4_K_M.gguf b/GLM4-9B-Neon-v2.Q4_K_M.gguf new file mode 100644 index 0000000..4c93e48 --- /dev/null +++ b/GLM4-9B-Neon-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4679b439516f5c93ce6747afaf3d55c9440ef070ebedf149f4a93640fa415393 +size 6166575680 diff --git a/GLM4-9B-Neon-v2.Q4_K_S.gguf b/GLM4-9B-Neon-v2.Q4_K_S.gguf new file mode 100644 index 0000000..bfdaa13 --- /dev/null +++ b/GLM4-9B-Neon-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f302c2e08f3b28a6b41ccc3486d7b9f7312207984a45714cd6f53ea9aaa49b6c +size 5758483008 diff --git a/GLM4-9B-Neon-v2.Q5_K_M.gguf b/GLM4-9B-Neon-v2.Q5_K_M.gguf new file mode 100644 index 0000000..457478c --- /dev/null +++ b/GLM4-9B-Neon-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3bc87d7c074c8ffbdffea2a69aeedc1bd73a2ad0dc5d652ed63f28291ac28fd +size 7050918464 diff --git a/GLM4-9B-Neon-v2.Q5_K_S.gguf b/GLM4-9B-Neon-v2.Q5_K_S.gguf new file mode 100644 index 0000000..b5e59af --- /dev/null +++ b/GLM4-9B-Neon-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1c2a537ec1b0dae658937e31240e341c2e20d7a0fc449838c4a1944ad29cdff +size 6697515584 diff --git a/GLM4-9B-Neon-v2.Q6_K.gguf b/GLM4-9B-Neon-v2.Q6_K.gguf new file mode 100644 index 0000000..dad24e9 --- /dev/null +++ b/GLM4-9B-Neon-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f167d31f3b1c08614ff7ef8a26e0659618296d6801845385b45d3a15690449 +size 8266644032 diff --git a/GLM4-9B-Neon-v2.Q8_0.gguf b/GLM4-9B-Neon-v2.Q8_0.gguf new file mode 100644 index 0000000..bac8b77 --- /dev/null +++ b/GLM4-9B-Neon-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e3cee9a4c35128dd7d5f203980c660184005d022654c94bdc665f6e2ada8de1 +size 9999612480 diff --git a/GLM4-9B-Neon-v2.f16.gguf b/GLM4-9B-Neon-v2.f16.gguf new file mode 100644 index 0000000..696ff6d --- /dev/null +++ b/GLM4-9B-Neon-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e79b69e5b0e4b5a54ea7db45f3a83766cd4b074a45eaea1b5d2083e9745e35da +size 18811583040 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ebeb3ec --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: allura-org/GLM4-9B-Neon-v2 +datasets: +- allura-org/Celeste-Filtered +- allura-org/neon-41k +- EVA-UNIT-01/Lilith-v0.2 +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/allura-org/GLM4-9B-Neon-v2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-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/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.Q2_K.gguf) | Q2_K | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.Q3_K_S.gguf) | Q3_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.Q3_K_M.gguf) | Q3_K_M | 5.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.Q3_K_L.gguf) | Q3_K_L | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.IQ4_XS.gguf) | IQ4_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.Q4_K_S.gguf) | Q4_K_S | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.Q4_K_M.gguf) | Q4_K_M | 6.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.Q5_K_S.gguf) | Q5_K_S | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.Q5_K_M.gguf) | Q5_K_M | 7.2 | | +| [GGUF](https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.Q6_K.gguf) | Q6_K | 8.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.Q8_0.gguf) | Q8_0 | 10.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GLM4-9B-Neon-v2-GGUF/resolve/main/GLM4-9B-Neon-v2.f16.gguf) | f16 | 18.9 | 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. + +