commit 23210fc9c6c3e079b96d101fc50b3ad1c8231102 Author: ModelHub XC Date: Sun Jul 5 21:33:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/0.5B-MoE-llama-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..be0f2aa --- /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 +0.5B-MoE-llama.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +0.5B-MoE-llama.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +0.5B-MoE-llama.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +0.5B-MoE-llama.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +0.5B-MoE-llama.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +0.5B-MoE-llama.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +0.5B-MoE-llama.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +0.5B-MoE-llama.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +0.5B-MoE-llama.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +0.5B-MoE-llama.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +0.5B-MoE-llama.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +0.5B-MoE-llama.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/0.5B-MoE-llama.IQ4_XS.gguf b/0.5B-MoE-llama.IQ4_XS.gguf new file mode 100644 index 0000000..f1d7a15 --- /dev/null +++ b/0.5B-MoE-llama.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce9f9384b091bb979579ced9917eb8a88a6d0ba4a3700dc2e54242dd09eb8aec +size 274472608 diff --git a/0.5B-MoE-llama.Q2_K.gguf b/0.5B-MoE-llama.Q2_K.gguf new file mode 100644 index 0000000..20af939 --- /dev/null +++ b/0.5B-MoE-llama.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d53078cce45e7100e1fbef1dc945dc55ee567127966c28334268680e1623fbba +size 263109280 diff --git a/0.5B-MoE-llama.Q3_K_L.gguf b/0.5B-MoE-llama.Q3_K_L.gguf new file mode 100644 index 0000000..cbe3f8d --- /dev/null +++ b/0.5B-MoE-llama.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe488e70453404df53508a84b006e88d7a39c9b29cfb0d8b79eaf7a5a362733 +size 296701600 diff --git a/0.5B-MoE-llama.Q3_K_M.gguf b/0.5B-MoE-llama.Q3_K_M.gguf new file mode 100644 index 0000000..2c6f757 --- /dev/null +++ b/0.5B-MoE-llama.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe19071bf951f45c80a6cd836a78c712ee58fe65a6bcf829e0d5e4abf63c5c81 +size 282601120 diff --git a/0.5B-MoE-llama.Q3_K_S.gguf b/0.5B-MoE-llama.Q3_K_S.gguf new file mode 100644 index 0000000..51d90ee --- /dev/null +++ b/0.5B-MoE-llama.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2891fcfdf2240fc66d76fd58ce2826fa65241ee9a980336578aa6cedc4a7b155 +size 263109280 diff --git a/0.5B-MoE-llama.Q4_K_M.gguf b/0.5B-MoE-llama.Q4_K_M.gguf new file mode 100644 index 0000000..98d87dc --- /dev/null +++ b/0.5B-MoE-llama.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e283c4c375678807b85a7e16e8f2f22005e8405721ddb71d3438bf93dc89b7ef +size 333035680 diff --git a/0.5B-MoE-llama.Q4_K_S.gguf b/0.5B-MoE-llama.Q4_K_S.gguf new file mode 100644 index 0000000..36de295 --- /dev/null +++ b/0.5B-MoE-llama.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f4fe7148a6e1852fe1ec38c7f7f529566bcafeb9dd35b05cd5cbdce7832836 +size 317898400 diff --git a/0.5B-MoE-llama.Q5_K_M.gguf b/0.5B-MoE-llama.Q5_K_M.gguf new file mode 100644 index 0000000..2c44a9d --- /dev/null +++ b/0.5B-MoE-llama.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb66c3a526beff478a33eec91ad5b9e4c9cb919f90bd0b100691b0de64d461f0 +size 358481056 diff --git a/0.5B-MoE-llama.Q5_K_S.gguf b/0.5B-MoE-llama.Q5_K_S.gguf new file mode 100644 index 0000000..1f5d9d9 --- /dev/null +++ b/0.5B-MoE-llama.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5f717147f939e5a676686dc7b060b25faa2583d22f6717361d3bc62663e600 +size 348403360 diff --git a/0.5B-MoE-llama.Q6_K.gguf b/0.5B-MoE-llama.Q6_K.gguf new file mode 100644 index 0000000..bb78b55 --- /dev/null +++ b/0.5B-MoE-llama.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:885daabfc187650e19146609a194ed0b80f47fbb115b84fc5bfec0a9b41fd3c9 +size 462193312 diff --git a/0.5B-MoE-llama.Q8_0.gguf b/0.5B-MoE-llama.Q8_0.gguf new file mode 100644 index 0000000..0755138 --- /dev/null +++ b/0.5B-MoE-llama.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110bc8c32e72bd864ddb84cd6eef2614e332f9cd0939c003a65461d592b7e506 +size 485334688 diff --git a/0.5B-MoE-llama.f16.gguf b/0.5B-MoE-llama.f16.gguf new file mode 100644 index 0000000..f197b62 --- /dev/null +++ b/0.5B-MoE-llama.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13dd0528ed89771a74acfb5765ba84a40c80ede2243e961bcc2fd097ec8e68b7 +size 912772768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..82907ca --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: reflex-ai/0.5B-MoE-llama +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/reflex-ai/0.5B-MoE-llama + + +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/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.IQ4_XS.gguf) | IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.Q3_K_L.gguf) | Q3_K_L | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.Q4_K_S.gguf) | Q4_K_S | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.Q4_K_M.gguf) | Q4_K_M | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/0.5B-MoE-llama-GGUF/resolve/main/0.5B-MoE-llama.f16.gguf) | f16 | 1.0 | 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. + +