commit 2c40854208345166b3b3a9619b32fe1c26839bfe Author: ModelHub XC Date: Fri Jul 24 02:37:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ablation-model-refinedweb-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fafd741 --- /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 +ablation-model-refinedweb.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ablation-model-refinedweb.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-model-refinedweb.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ablation-model-refinedweb.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-model-refinedweb.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-model-refinedweb.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-model-refinedweb.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-model-refinedweb.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ablation-model-refinedweb.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ablation-model-refinedweb.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ablation-model-refinedweb.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ablation-model-refinedweb.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b783180 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: HuggingFaceFW/ablation-model-refinedweb +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/HuggingFaceFW/ablation-model-refinedweb + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ablation-model-refinedweb-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/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.Q4_K_S.gguf) | Q4_K_S | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.Q5_K_M.gguf) | Q5_K_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ablation-model-refinedweb-GGUF/resolve/main/ablation-model-refinedweb.f16.gguf) | f16 | 3.5 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/ablation-model-refinedweb.IQ4_XS.gguf b/ablation-model-refinedweb.IQ4_XS.gguf new file mode 100644 index 0000000..3a12cc3 --- /dev/null +++ b/ablation-model-refinedweb.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c8e4e3a691bc4f745723e99588ce2d4b3b3940401de4ee50fee969cac736326 +size 950141696 diff --git a/ablation-model-refinedweb.Q2_K.gguf b/ablation-model-refinedweb.Q2_K.gguf new file mode 100644 index 0000000..a52e767 --- /dev/null +++ b/ablation-model-refinedweb.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:313ff6cbad4f4a4cbda9e972eb0066c537e6799242b98fb40462969a7c3becfc +size 676463360 diff --git a/ablation-model-refinedweb.Q3_K_L.gguf b/ablation-model-refinedweb.Q3_K_L.gguf new file mode 100644 index 0000000..d3bb43d --- /dev/null +++ b/ablation-model-refinedweb.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a273ec5a86a1df104bb016e0ab873d70493f7116eb7927503b70c873554466 +size 934413056 diff --git a/ablation-model-refinedweb.Q3_K_M.gguf b/ablation-model-refinedweb.Q3_K_M.gguf new file mode 100644 index 0000000..20e6454 --- /dev/null +++ b/ablation-model-refinedweb.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:897181a60f2f3aa6acc289fd4cfe09333e1309f98348f510f4170e84f32e6b7a +size 862061312 diff --git a/ablation-model-refinedweb.Q3_K_S.gguf b/ablation-model-refinedweb.Q3_K_S.gguf new file mode 100644 index 0000000..3c0cce7 --- /dev/null +++ b/ablation-model-refinedweb.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f012898eea8370411085be869cde846c83206a9ed7ae9323dae61d3f87cdf945 +size 778699520 diff --git a/ablation-model-refinedweb.Q4_K_M.gguf b/ablation-model-refinedweb.Q4_K_M.gguf new file mode 100644 index 0000000..a790e89 --- /dev/null +++ b/ablation-model-refinedweb.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c72c09c8d61ebf54bfa5eb7fa5461ef56afe7965461be84007bd2ba638571590 +size 1057489664 diff --git a/ablation-model-refinedweb.Q4_K_S.gguf b/ablation-model-refinedweb.Q4_K_S.gguf new file mode 100644 index 0000000..e8e33d8 --- /dev/null +++ b/ablation-model-refinedweb.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4370902ffac586b7ff230b9bd1a936a0706c9ae0016125ede25d47b8ff5df8d3 +size 1000997632 diff --git a/ablation-model-refinedweb.Q5_K_M.gguf b/ablation-model-refinedweb.Q5_K_M.gguf new file mode 100644 index 0000000..4ead750 --- /dev/null +++ b/ablation-model-refinedweb.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e44b2159c1398d196e1f31b4b7501770f379e57e32d3ce5b6bd94becee40ef +size 1227358976 diff --git a/ablation-model-refinedweb.Q5_K_S.gguf b/ablation-model-refinedweb.Q5_K_S.gguf new file mode 100644 index 0000000..794c4fa --- /dev/null +++ b/ablation-model-refinedweb.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5719e90f00db7a5a632aad052184ec771ce17e739d778304b9c0af9b5edd4250 +size 1193935616 diff --git a/ablation-model-refinedweb.Q6_K.gguf b/ablation-model-refinedweb.Q6_K.gguf new file mode 100644 index 0000000..5eab475 --- /dev/null +++ b/ablation-model-refinedweb.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:782d3e9efe92c607f888388fe6e5ffd91a89d7bbf0bfaa5de4a881ffc215079c +size 1407845120 diff --git a/ablation-model-refinedweb.Q8_0.gguf b/ablation-model-refinedweb.Q8_0.gguf new file mode 100644 index 0000000..8bfe18f --- /dev/null +++ b/ablation-model-refinedweb.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f485ad6dfb9883f55e9a9a37c77b6a6bc29ec8b2415f783d96b155c99b5fbcaa +size 1822850304 diff --git a/ablation-model-refinedweb.f16.gguf b/ablation-model-refinedweb.f16.gguf new file mode 100644 index 0000000..a458c3a --- /dev/null +++ b/ablation-model-refinedweb.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:558d4c1b6d4813b976a754bb0658a2d8623c02d459249bf26b356f0472bfb0e7 +size 3429321984