commit 9ebc87cb903654988f08511b0fcd493c46ad28d1 Author: ModelHub XC Date: Sun Jun 14 04:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Pretrained-SCP-1B-QLoRA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53fc144 --- /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 +Pretrained-SCP-1B-QLoRA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Pretrained-SCP-1B-QLoRA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Pretrained-SCP-1B-QLoRA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Pretrained-SCP-1B-QLoRA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pretrained-SCP-1B-QLoRA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pretrained-SCP-1B-QLoRA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pretrained-SCP-1B-QLoRA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pretrained-SCP-1B-QLoRA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pretrained-SCP-1B-QLoRA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pretrained-SCP-1B-QLoRA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Pretrained-SCP-1B-QLoRA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Pretrained-SCP-1B-QLoRA.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Pretrained-SCP-1B-QLoRA.IQ4_XS.gguf b/Pretrained-SCP-1B-QLoRA.IQ4_XS.gguf new file mode 100644 index 0000000..0375458 --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78d4726fa37cd8934d03502b348c4c59c04ca8692a24d03952eb9de8b7bf5f53 +size 748385152 diff --git a/Pretrained-SCP-1B-QLoRA.Q2_K.gguf b/Pretrained-SCP-1B-QLoRA.Q2_K.gguf new file mode 100644 index 0000000..305ef3e --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:062c5465d34b594ae768db3a12f91a52e2c9e7cebe165c88cf31a3bcf6756761 +size 580875136 diff --git a/Pretrained-SCP-1B-QLoRA.Q3_K_L.gguf b/Pretrained-SCP-1B-QLoRA.Q3_K_L.gguf new file mode 100644 index 0000000..69f15d8 --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16951d93f8f4b020f051ebc910dd6b3201f0d33d82223a48211a37c8685e619c +size 732525440 diff --git a/Pretrained-SCP-1B-QLoRA.Q3_K_M.gguf b/Pretrained-SCP-1B-QLoRA.Q3_K_M.gguf new file mode 100644 index 0000000..8f034a2 --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6419ac115b44c7fd9ad474bb817e6a8c64378a65486f71eeb006ffb7cd4981a9 +size 690844544 diff --git a/Pretrained-SCP-1B-QLoRA.Q3_K_S.gguf b/Pretrained-SCP-1B-QLoRA.Q3_K_S.gguf new file mode 100644 index 0000000..f01ca54 --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38156c31843de0916c766f826fb7cab6aa6a78b972bb88d35e59223624d17946 +size 641692544 diff --git a/Pretrained-SCP-1B-QLoRA.Q4_K_M.gguf b/Pretrained-SCP-1B-QLoRA.Q4_K_M.gguf new file mode 100644 index 0000000..19a08b7 --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1c7f097d81db552688a2981b8566c13518a723687026b336ee9e18aa37eb40 +size 807695232 diff --git a/Pretrained-SCP-1B-QLoRA.Q4_K_S.gguf b/Pretrained-SCP-1B-QLoRA.Q4_K_S.gguf new file mode 100644 index 0000000..9eac64a --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a2c5b1c199e73c215d8de9ee95e4ef15a5d4040c1fa99e30a43a8dd2202844 +size 775648128 diff --git a/Pretrained-SCP-1B-QLoRA.Q5_K_M.gguf b/Pretrained-SCP-1B-QLoRA.Q5_K_M.gguf new file mode 100644 index 0000000..2e12c10 --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90e2f861460ecf755e3cb15ed85a775e65b390c70bbb6a2d792d421b8147c9da +size 911504256 diff --git a/Pretrained-SCP-1B-QLoRA.Q5_K_S.gguf b/Pretrained-SCP-1B-QLoRA.Q5_K_S.gguf new file mode 100644 index 0000000..56bcaaa --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:304bf0ed33dd740c9a6d2118593ea6f5a67facb35700bc65d7646c0e557ab672 +size 892564352 diff --git a/Pretrained-SCP-1B-QLoRA.Q6_K.gguf b/Pretrained-SCP-1B-QLoRA.Q6_K.gguf new file mode 100644 index 0000000..dcad998 --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fe62a933faa29e95ecebe0c942c4ea0afbfaaefd3046347cbdd6d04357833fc +size 1021801344 diff --git a/Pretrained-SCP-1B-QLoRA.Q8_0.gguf b/Pretrained-SCP-1B-QLoRA.Q8_0.gguf new file mode 100644 index 0000000..31145d1 --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59c7719dae078511cdb59793dbdce59afbdb221689be058bd280e4e00f39fffa +size 1321083776 diff --git a/Pretrained-SCP-1B-QLoRA.f16.gguf b/Pretrained-SCP-1B-QLoRA.f16.gguf new file mode 100644 index 0000000..6fba456 --- /dev/null +++ b/Pretrained-SCP-1B-QLoRA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8637473a1fc57c51f5432a2c297abc2bcae6c9c1180489b60a57fc912d4c996e +size 2479596416 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0ea39d1 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: AiAF/Pretrained-SCP-1B-QLoRA +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/AiAF/Pretrained-SCP-1B-QLoRA + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-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/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Pretrained-SCP-1B-QLoRA-GGUF/resolve/main/Pretrained-SCP-1B-QLoRA.f16.gguf) | f16 | 2.6 | 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. + +