commit c352bc24d6c37a097348a2dd10ce403e3448c3a7 Author: ModelHub XC Date: Sat May 23 23:53:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ByteGPT-r1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..162299d --- /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 +ByteGPT-r1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ByteGPT-r1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ByteGPT-r1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ByteGPT-r1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ByteGPT-r1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ByteGPT-r1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ByteGPT-r1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ByteGPT-r1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ByteGPT-r1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ByteGPT-r1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ByteGPT-r1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ByteGPT-r1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ByteGPT-r1.IQ4_XS.gguf b/ByteGPT-r1.IQ4_XS.gguf new file mode 100644 index 0000000..33571ef --- /dev/null +++ b/ByteGPT-r1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e880263dd346844835132418a46ea685295841aa38f9f9c717004d8039a9679 +size 1026162816 diff --git a/ByteGPT-r1.Q2_K.gguf b/ByteGPT-r1.Q2_K.gguf new file mode 100644 index 0000000..695ab91 --- /dev/null +++ b/ByteGPT-r1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ab67083c92e22cd57393a875209554a6793eb490c4bf946f34ba3ca851deb9 +size 752880768 diff --git a/ByteGPT-r1.Q3_K_L.gguf b/ByteGPT-r1.Q3_K_L.gguf new file mode 100644 index 0000000..c6bb28d --- /dev/null +++ b/ByteGPT-r1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14f9ee9c22f95dbb7a6402fa292c6a844e835ff9847faedfc8de72472ff7aafd +size 980440704 diff --git a/ByteGPT-r1.Q3_K_M.gguf b/ByteGPT-r1.Q3_K_M.gguf new file mode 100644 index 0000000..e4e48d8 --- /dev/null +++ b/ByteGPT-r1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda71d3c93bda54511a0e98a61090d4b68ad0b30d3d50301e50f86ba982b4970 +size 924456576 diff --git a/ByteGPT-r1.Q3_K_S.gguf b/ByteGPT-r1.Q3_K_S.gguf new file mode 100644 index 0000000..d450d5b --- /dev/null +++ b/ByteGPT-r1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fbeeb3b6b8f6890414c2a9c923ad71242616eb9ee12b01143db3165b643b5b6 +size 861222528 diff --git a/ByteGPT-r1.Q4_K_M.gguf b/ByteGPT-r1.Q4_K_M.gguf new file mode 100644 index 0000000..9c7b16f --- /dev/null +++ b/ByteGPT-r1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f6f4dce2be815f069e566d4a15405c31e914415c19b9e04ceb82ce644cd95e +size 1117321344 diff --git a/ByteGPT-r1.Q4_K_S.gguf b/ByteGPT-r1.Q4_K_S.gguf new file mode 100644 index 0000000..2946a5a --- /dev/null +++ b/ByteGPT-r1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea5a9ec0ea177bc8aea7f57529b423a1f99478dd7fa291cf01916facf5e31d19 +size 1071585408 diff --git a/ByteGPT-r1.Q5_K_M.gguf b/ByteGPT-r1.Q5_K_M.gguf new file mode 100644 index 0000000..434db95 --- /dev/null +++ b/ByteGPT-r1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31454755807dd9ad345803a999854539511402c2a402aa27100f3d17d82c90d5 +size 1285494912 diff --git a/ByteGPT-r1.Q5_K_S.gguf b/ByteGPT-r1.Q5_K_S.gguf new file mode 100644 index 0000000..e0d9b51 --- /dev/null +++ b/ByteGPT-r1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7400eb64e7a84d2655a8fb7da61e98bea2c31c88ec11fe936f1e45be47f1f6bf +size 1259174016 diff --git a/ByteGPT-r1.Q6_K.gguf b/ByteGPT-r1.Q6_K.gguf new file mode 100644 index 0000000..484e35c --- /dev/null +++ b/ByteGPT-r1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bd73f7ec9d7d801b9d8cb29db3f4411d5d3193c7bf3fe987504687e93581474 +size 1464179328 diff --git a/ByteGPT-r1.Q8_0.gguf b/ByteGPT-r1.Q8_0.gguf new file mode 100644 index 0000000..376409d --- /dev/null +++ b/ByteGPT-r1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76138ecb43149617a79e1a38975854e715558ac28c17879bf39cde8428278d8d +size 1894532736 diff --git a/ByteGPT-r1.f16.gguf b/ByteGPT-r1.f16.gguf new file mode 100644 index 0000000..73665e6 --- /dev/null +++ b/ByteGPT-r1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed896d2632c4fc12cd754a42069ae0e231c4bdf2c171a588b095399a80055fba +size 3560416896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..005e052 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: ijktech/ByteGPT-r1 +datasets: +- custom +- web +language: en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- gpt +- distillation +- mobile +- embedded +- onnx +--- +## About + + + + + + +static quants of https://huggingface.co/ijktech/ByteGPT-r1 + + +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/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ByteGPT-r1-GGUF/resolve/main/ByteGPT-r1.f16.gguf) | f16 | 3.7 | 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. + +