commit 28a497814916e91c861b7395adf291035d7a3a9b Author: ModelHub XC Date: Tue Apr 14 01:38:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RATE-0.6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5221db9 --- /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 +RATE-0.6B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +RATE-0.6B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RATE-0.6B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RATE-0.6B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RATE-0.6B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RATE-0.6B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RATE-0.6B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RATE-0.6B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RATE-0.6B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RATE-0.6B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RATE-0.6B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RATE-0.6B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/RATE-0.6B.IQ4_XS.gguf b/RATE-0.6B.IQ4_XS.gguf new file mode 100644 index 0000000..e70a715 --- /dev/null +++ b/RATE-0.6B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e5f791149e06d949cfc52c17b8dc539970bf8e8dacc71e6596faf6cd8f9890 +size 369047680 diff --git a/RATE-0.6B.Q2_K.gguf b/RATE-0.6B.Q2_K.gguf new file mode 100644 index 0000000..5aadb68 --- /dev/null +++ b/RATE-0.6B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2703c971d123a79d31767c0720f4ec559dfb031dd28c96d09ff06830243ca6d +size 296007808 diff --git a/RATE-0.6B.Q3_K_L.gguf b/RATE-0.6B.Q3_K_L.gguf new file mode 100644 index 0000000..a0a5bcb --- /dev/null +++ b/RATE-0.6B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cae6ef04c918a82933f7bb4257443aec168e01ad81dd4bb159ddb2ceb6d97c04 +size 368261248 diff --git a/RATE-0.6B.Q3_K_M.gguf b/RATE-0.6B.Q3_K_M.gguf new file mode 100644 index 0000000..d117e57 --- /dev/null +++ b/RATE-0.6B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c17c1f0073d16391ad786613114d73f040d91b9e6c97964b07eda100094f33 +size 346896512 diff --git a/RATE-0.6B.Q3_K_S.gguf b/RATE-0.6B.Q3_K_S.gguf new file mode 100644 index 0000000..a8baa1a --- /dev/null +++ b/RATE-0.6B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:471a6d12fd7ea4ef324bfe507d7ba3cecc8e18c558a0280c14db0378298f14b1 +size 322844800 diff --git a/RATE-0.6B.Q4_K_M.gguf b/RATE-0.6B.Q4_K_M.gguf new file mode 100644 index 0000000..5739227 --- /dev/null +++ b/RATE-0.6B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20107e644bb1db33d99c69c50f3ee15c4f5bc60e98410cc218293bda7a72c1a4 +size 396474496 diff --git a/RATE-0.6B.Q4_K_S.gguf b/RATE-0.6B.Q4_K_S.gguf new file mode 100644 index 0000000..7e7402c --- /dev/null +++ b/RATE-0.6B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fd4446a12be80941e5c86ea0a56a807ca33346606dec8f1ca69024e782b1275 +size 383039616 diff --git a/RATE-0.6B.Q5_K_M.gguf b/RATE-0.6B.Q5_K_M.gguf new file mode 100644 index 0000000..a9d72a9 --- /dev/null +++ b/RATE-0.6B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78d4153ac34e0d3f7f5e0f8cd78eaab70f3f3f7304ccd37dedf70ed21339f518 +size 444184704 diff --git a/RATE-0.6B.Q5_K_S.gguf b/RATE-0.6B.Q5_K_S.gguf new file mode 100644 index 0000000..f2f2143 --- /dev/null +++ b/RATE-0.6B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca31f1044d12d0a977e24acc4c60a68a765892cab31b608b152a853b3318329d +size 436385920 diff --git a/RATE-0.6B.Q6_K.gguf b/RATE-0.6B.Q6_K.gguf new file mode 100644 index 0000000..44efd48 --- /dev/null +++ b/RATE-0.6B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bc852e6ab823f54951c7bb2e9d11898bc9b70e973d325b94bdd6bfa5557038f +size 494876800 diff --git a/RATE-0.6B.Q8_0.gguf b/RATE-0.6B.Q8_0.gguf new file mode 100644 index 0000000..f105053 --- /dev/null +++ b/RATE-0.6B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8282ef439d16d9e853cb05967fddc7782d2f9cf457b196c0d327ef7f092b7e +size 639150528 diff --git a/RATE-0.6B.f16.gguf b/RATE-0.6B.f16.gguf new file mode 100644 index 0000000..a2f425c --- /dev/null +++ b/RATE-0.6B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df861b34575194202fc568e73823ba0f5d96b190f06423fd4fe5183742f50b96 +size 1197629568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..00207d1 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Gnociew/RATE-0.6B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Gnociew/RATE-0.6B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#RATE-0.6B-GGUF).*** + +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/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RATE-0.6B-GGUF/resolve/main/RATE-0.6B.f16.gguf) | f16 | 1.3 | 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. + +