commit 0585e6c1c1c9d688b9d8e06560405140700e771f Author: ModelHub XC Date: Fri May 8 03:34:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/pythia-intervention-410m-deduped-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5531f03 --- /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 +pythia-intervention-410m-deduped.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +pythia-intervention-410m-deduped.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +pythia-intervention-410m-deduped.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +pythia-intervention-410m-deduped.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +pythia-intervention-410m-deduped.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +pythia-intervention-410m-deduped.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +pythia-intervention-410m-deduped.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +pythia-intervention-410m-deduped.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +pythia-intervention-410m-deduped.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +pythia-intervention-410m-deduped.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +pythia-intervention-410m-deduped.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +pythia-intervention-410m-deduped.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..27b1005 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: EleutherAI/pythia-intervention-410m-deduped +datasets: +- EleutherAI/pile +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/EleutherAI/pythia-intervention-410m-deduped + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-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/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.Q4_K_M.gguf) | Q4_K_M | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/pythia-intervention-410m-deduped-GGUF/resolve/main/pythia-intervention-410m-deduped.f16.gguf) | f16 | 0.9 | 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. + + diff --git a/pythia-intervention-410m-deduped.IQ4_XS.gguf b/pythia-intervention-410m-deduped.IQ4_XS.gguf new file mode 100644 index 0000000..cfc6c76 --- /dev/null +++ b/pythia-intervention-410m-deduped.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcbab1734fc71b8f6cd2923bc7c28c642c3add6c50e9a4ea155980b4497a7686 +size 235091008 diff --git a/pythia-intervention-410m-deduped.Q2_K.gguf b/pythia-intervention-410m-deduped.Q2_K.gguf new file mode 100644 index 0000000..a893946 --- /dev/null +++ b/pythia-intervention-410m-deduped.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d85e04032e44910f65a4eedff2172aac80c310d475a37b4f32e4a289582b4f +size 174099520 diff --git a/pythia-intervention-410m-deduped.Q3_K_L.gguf b/pythia-intervention-410m-deduped.Q3_K_L.gguf new file mode 100644 index 0000000..2b9b383 --- /dev/null +++ b/pythia-intervention-410m-deduped.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d9c248175743217a9a5a4881edb0f4a4718547990882195e29b3ce73c702f31 +size 239689792 diff --git a/pythia-intervention-410m-deduped.Q3_K_M.gguf b/pythia-intervention-410m-deduped.Q3_K_M.gguf new file mode 100644 index 0000000..639e33e --- /dev/null +++ b/pythia-intervention-410m-deduped.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e84773416d78ef93d0a95a0ca6f837d2b5902f93b4361b4aab8ba808cc76418 +size 224485440 diff --git a/pythia-intervention-410m-deduped.Q3_K_S.gguf b/pythia-intervention-410m-deduped.Q3_K_S.gguf new file mode 100644 index 0000000..5d475b2 --- /dev/null +++ b/pythia-intervention-410m-deduped.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5087db24331a0a8e8e3385efed538e1f0b15bd06d1d18282185a386051980fa4 +size 197222464 diff --git a/pythia-intervention-410m-deduped.Q4_K_M.gguf b/pythia-intervention-410m-deduped.Q4_K_M.gguf new file mode 100644 index 0000000..331069b --- /dev/null +++ b/pythia-intervention-410m-deduped.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d78209b28027e03161abe6a0a403b057e47e3030035692a54015936cb20c1c68 +size 266585152 diff --git a/pythia-intervention-410m-deduped.Q4_K_S.gguf b/pythia-intervention-410m-deduped.Q4_K_S.gguf new file mode 100644 index 0000000..2107924 --- /dev/null +++ b/pythia-intervention-410m-deduped.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7737f4a7427916c195e24638d2579f678f11c99a5d7433b6bd0b292e256d497a +size 245744704 diff --git a/pythia-intervention-410m-deduped.Q5_K_M.gguf b/pythia-intervention-410m-deduped.Q5_K_M.gguf new file mode 100644 index 0000000..fb51ac6 --- /dev/null +++ b/pythia-intervention-410m-deduped.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96cff122b2587a3e4e0263ad249f9db5f9c682544d0428390edbe9f651d17bd7 +size 305071168 diff --git a/pythia-intervention-410m-deduped.Q5_K_S.gguf b/pythia-intervention-410m-deduped.Q5_K_S.gguf new file mode 100644 index 0000000..bab6d0b --- /dev/null +++ b/pythia-intervention-410m-deduped.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:365fc0bc5633cc39bfeec228d7e73abb9bfb0ea2a858daa0f93a352e7193fdb0 +size 288359488 diff --git a/pythia-intervention-410m-deduped.Q6_K.gguf b/pythia-intervention-410m-deduped.Q6_K.gguf new file mode 100644 index 0000000..4646366 --- /dev/null +++ b/pythia-intervention-410m-deduped.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b22cf80a8f908fdd564c13de1853a52e1e22de8a5941a061bc42ac1b3dd27c13 +size 335308864 diff --git a/pythia-intervention-410m-deduped.Q8_0.gguf b/pythia-intervention-410m-deduped.Q8_0.gguf new file mode 100644 index 0000000..cb6566a --- /dev/null +++ b/pythia-intervention-410m-deduped.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd00dff6e77c48b4c9ef7a46e2d786c758a10e59d8e461f84b5844523f5ffb2 +size 433397824 diff --git a/pythia-intervention-410m-deduped.f16.gguf b/pythia-intervention-410m-deduped.f16.gguf new file mode 100644 index 0000000..4b1cbd6 --- /dev/null +++ b/pythia-intervention-410m-deduped.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3492d9e6cd7fc9e5775d3b286642ce66bc2829adb088a5bddd39a6ceb6ba8723 +size 813097024