commit 7e98bcca17c17dce09a23605b2b10fe19ce89d34 Author: ModelHub XC Date: Sat May 9 07:27:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-8B-ERP-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5300369 --- /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 +Qwen3-8B-ERP-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-ERP-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-8B-ERP-v0.1.IQ4_XS.gguf b/Qwen3-8B-ERP-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..1aebd96 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d578742292e6beb877b3179d72acd8572ebe251784da3be39aa9d43e00ec31c +size 4593296960 diff --git a/Qwen3-8B-ERP-v0.1.Q2_K.gguf b/Qwen3-8B-ERP-v0.1.Q2_K.gguf new file mode 100644 index 0000000..936dbbb --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dade0ca899f79a9475acc6bb1452bea6c618ab776ea9714116767583e260fa4e +size 3281733184 diff --git a/Qwen3-8B-ERP-v0.1.Q3_K_L.gguf b/Qwen3-8B-ERP-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..64f12e6 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de5c3dbd21a25fe096444897c8544d96dd7337f4de9b5c6c266b97d4fb5407e2 +size 4431394368 diff --git a/Qwen3-8B-ERP-v0.1.Q3_K_M.gguf b/Qwen3-8B-ERP-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..4191ca7 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2568829e18b6db6d83de2bfe62dad5934618295c172acf71d57a37a2fcf8492b +size 4124161600 diff --git a/Qwen3-8B-ERP-v0.1.Q3_K_S.gguf b/Qwen3-8B-ERP-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..4e87663 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6179d11fccc5fd6c5f4813e115b3677bcc337e2841f7c96f1f3d174ae5bbaea +size 3769611840 diff --git a/Qwen3-8B-ERP-v0.1.Q4_K_M.gguf b/Qwen3-8B-ERP-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..500c492 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd1b9d7fd0ec805c384294537bb22af7c4be14457e7fe06f773efff7d871763 +size 5027784256 diff --git a/Qwen3-8B-ERP-v0.1.Q4_K_S.gguf b/Qwen3-8B-ERP-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..d4ef10f --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36662a049a0e553ec42cafe35b6bd8f541ad7c1d56829b2985e382942ca2ca29 +size 4802012736 diff --git a/Qwen3-8B-ERP-v0.1.Q5_K_M.gguf b/Qwen3-8B-ERP-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..8bf6f98 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb67a14dfe6b3a074d248a18b5947f0ec3d9345fb6a0dfffc34aa90555843c3 +size 5851113024 diff --git a/Qwen3-8B-ERP-v0.1.Q5_K_S.gguf b/Qwen3-8B-ERP-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..ae47e85 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fead68aea03c68bb7cc88d4fd240e2b576c7d1883afaa9f3c6139a4b3d88763 +size 5720761920 diff --git a/Qwen3-8B-ERP-v0.1.Q6_K.gguf b/Qwen3-8B-ERP-v0.1.Q6_K.gguf new file mode 100644 index 0000000..d549013 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b3e8d5e6fcca6c8b56aae75b80738b47d557119a98feb2aa10c19ab7166181f +size 6725899840 diff --git a/Qwen3-8B-ERP-v0.1.Q8_0.gguf b/Qwen3-8B-ERP-v0.1.Q8_0.gguf new file mode 100644 index 0000000..300c2d2 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94d3885a6fde10629875add7b2c71b6a957c83b6bd7657007c5a060fe17bf3c8 +size 8709518912 diff --git a/Qwen3-8B-ERP-v0.1.f16.gguf b/Qwen3-8B-ERP-v0.1.f16.gguf new file mode 100644 index 0000000..d737024 --- /dev/null +++ b/Qwen3-8B-ERP-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23d7e51164d2c540a7a00d83a31464050dc02f2a53f196360548645a143c8b1 +size 16388044352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a11d3e9 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Aratako/Qwen3-8B-ERP-v0.1 +language: +- ja +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Aratako/Qwen3-8B-ERP-v0.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-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/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-ERP-v0.1-GGUF/resolve/main/Qwen3-8B-ERP-v0.1.f16.gguf) | f16 | 16.5 | 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. + +