commit 90fdf63cc336a5bb7e05d7927e99383ab50d0b03 Author: ModelHub XC Date: Sat Jul 18 04:47:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ArlowGPT-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1096f4f --- /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 +ArlowGPT-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArlowGPT-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ArlowGPT-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ArlowGPT-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ArlowGPT-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +ArlowGPT-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArlowGPT-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArlowGPT-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ArlowGPT-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArlowGPT-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArlowGPT-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArlowGPT-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ArlowGPT-8B.IQ4_XS.gguf b/ArlowGPT-8B.IQ4_XS.gguf new file mode 100644 index 0000000..a9fe905 --- /dev/null +++ b/ArlowGPT-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:885487e232b217f7d5aac97aff02489b01fe6773f97c4ec45ffe7ad51b340176 +size 4484368000 diff --git a/ArlowGPT-8B.Q2_K.gguf b/ArlowGPT-8B.Q2_K.gguf new file mode 100644 index 0000000..68a9632 --- /dev/null +++ b/ArlowGPT-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd789759b3701d930559b73298762bb8c8714193d9e1c27350eb1500d976c2d +size 3179136640 diff --git a/ArlowGPT-8B.Q3_K_L.gguf b/ArlowGPT-8B.Q3_K_L.gguf new file mode 100644 index 0000000..5a6e1cf --- /dev/null +++ b/ArlowGPT-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f098d97b373abb129992e4ff72f3e47efcb0841f33822531860d345f7b0d8443 +size 4321961600 diff --git a/ArlowGPT-8B.Q3_K_M.gguf b/ArlowGPT-8B.Q3_K_M.gguf new file mode 100644 index 0000000..d6160b8 --- /dev/null +++ b/ArlowGPT-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98da31b00509446ff64949ceee017146a8cd8831e066c9a864594abfe5f26d37 +size 4018923136 diff --git a/ArlowGPT-8B.Q3_K_S.gguf b/ArlowGPT-8B.Q3_K_S.gguf new file mode 100644 index 0000000..71d5ae0 --- /dev/null +++ b/ArlowGPT-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205bc0fcf3a2cc283406f61c5971379b5cddbee939cf3266e4c36d376441ed02 +size 3664504448 diff --git a/ArlowGPT-8B.Q4_K_M.gguf b/ArlowGPT-8B.Q4_K_M.gguf new file mode 100644 index 0000000..ffd6beb --- /dev/null +++ b/ArlowGPT-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18d9c624030a5e72f7f777680374337bdadad212917daa6646c11d70ced24b62 +size 4920739456 diff --git a/ArlowGPT-8B.Q4_K_S.gguf b/ArlowGPT-8B.Q4_K_S.gguf new file mode 100644 index 0000000..56a2afd --- /dev/null +++ b/ArlowGPT-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8557dfdd6e8b5e9122f22e23a82cbe7624bf82bba3a2e89cc5029c55949c5cf4 +size 4692674176 diff --git a/ArlowGPT-8B.Q5_K_M.gguf b/ArlowGPT-8B.Q5_K_M.gguf new file mode 100644 index 0000000..e47822a --- /dev/null +++ b/ArlowGPT-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df0d628df1a31c5ee0b495877e9baa510994750bca8fcde94d0cb4acb73ebfe6 +size 5732992640 diff --git a/ArlowGPT-8B.Q5_K_S.gguf b/ArlowGPT-8B.Q5_K_S.gguf new file mode 100644 index 0000000..0c98b20 --- /dev/null +++ b/ArlowGPT-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16329300d644735232fef480420ebc78e9948a950db27901790c5cc42e18b377 +size 5599299200 diff --git a/ArlowGPT-8B.Q6_K.gguf b/ArlowGPT-8B.Q6_K.gguf new file mode 100644 index 0000000..22867fc --- /dev/null +++ b/ArlowGPT-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e95bddbfd7ed26be465a6f47143e653eb2c6df155d2b7ac58ffb08e3bd666e35 +size 6596011648 diff --git a/ArlowGPT-8B.Q8_0.gguf b/ArlowGPT-8B.Q8_0.gguf new file mode 100644 index 0000000..3b10cbc --- /dev/null +++ b/ArlowGPT-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:831c9d36e31c09a974908340f7049bd8a650cba5140af22c6fcab15bb0258c62 +size 8540776064 diff --git a/ArlowGPT-8B.f16.gguf b/ArlowGPT-8B.f16.gguf new file mode 100644 index 0000000..282e672 --- /dev/null +++ b/ArlowGPT-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:335caacb9f0e4a3a686f5b468f47134e5bf40691d832d8491e1facb428a0b64b +size 16068896384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..de6f7af --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: yuchenxie/ArlowGPT-8B +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/yuchenxie/ArlowGPT-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ArlowGPT-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ArlowGPT-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/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ArlowGPT-8B-GGUF/resolve/main/ArlowGPT-8B.f16.gguf) | f16 | 16.2 | 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. + +