commit 381615f03fa964ad958a1d0e1bc604103e6b4689 Author: ModelHub XC Date: Thu Jun 25 14:43:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/128-goldfish-loss-llama-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9b69a60 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +128-goldfish-loss-llama-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +128-goldfish-loss-llama-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/128-goldfish-loss-llama-1B.IQ3_M.gguf b/128-goldfish-loss-llama-1B.IQ3_M.gguf new file mode 100644 index 0000000..27c882d --- /dev/null +++ b/128-goldfish-loss-llama-1B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b09b42cd5f662acb0c6bea1946541a70e5b7d8e0baaaa61ffb3f18e9eae815dc +size 516193824 diff --git a/128-goldfish-loss-llama-1B.IQ3_S.gguf b/128-goldfish-loss-llama-1B.IQ3_S.gguf new file mode 100644 index 0000000..0726856 --- /dev/null +++ b/128-goldfish-loss-llama-1B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d15d54df5604a6eb11a66299a2c9b2e34a821f21dc7ea07a724bd4fe071da294 +size 500874784 diff --git a/128-goldfish-loss-llama-1B.IQ3_XS.gguf b/128-goldfish-loss-llama-1B.IQ3_XS.gguf new file mode 100644 index 0000000..125233d --- /dev/null +++ b/128-goldfish-loss-llama-1B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee0a489f77b87957cca1f90dab3f2d2e03bf3d34b7a350d69fe752b4c56445ff +size 477625888 diff --git a/128-goldfish-loss-llama-1B.IQ4_XS.gguf b/128-goldfish-loss-llama-1B.IQ4_XS.gguf new file mode 100644 index 0000000..c1e758d --- /dev/null +++ b/128-goldfish-loss-llama-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd1cebee8afe8fc32ab3254a81b01dbe5962520e20287a837814d7a9a03af0e +size 609807904 diff --git a/128-goldfish-loss-llama-1B.Q2_K.gguf b/128-goldfish-loss-llama-1B.Q2_K.gguf new file mode 100644 index 0000000..75f5a94 --- /dev/null +++ b/128-goldfish-loss-llama-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de9174c734008eeab83ab318600d48959c6e9380e53d44ed48086410cc2cacf3 +size 432131616 diff --git a/128-goldfish-loss-llama-1B.Q3_K_L.gguf b/128-goldfish-loss-llama-1B.Q3_K_L.gguf new file mode 100644 index 0000000..41671a1 --- /dev/null +++ b/128-goldfish-loss-llama-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5b34e2eeed598727185b5a9178dbcf194cfc06794e3030e8429c7efdf05099 +size 591527456 diff --git a/128-goldfish-loss-llama-1B.Q3_K_M.gguf b/128-goldfish-loss-llama-1B.Q3_K_M.gguf new file mode 100644 index 0000000..cc7de6c --- /dev/null +++ b/128-goldfish-loss-llama-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a614f14f45db31a3969d7b34527711be047eea4f63053c3d762c6cfaa8072f39 +size 548404768 diff --git a/128-goldfish-loss-llama-1B.Q3_K_S.gguf b/128-goldfish-loss-llama-1B.Q3_K_S.gguf new file mode 100644 index 0000000..f206261 --- /dev/null +++ b/128-goldfish-loss-llama-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2efa058a743b3046859e726ec994f5ed15debebd030048d0590b1862e9b6648e +size 499342880 diff --git a/128-goldfish-loss-llama-1B.Q4_K_M.gguf b/128-goldfish-loss-llama-1B.Q4_K_M.gguf new file mode 100644 index 0000000..1fde68c --- /dev/null +++ b/128-goldfish-loss-llama-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285a7470966164595941c704b707e36e90a569b7786670c8790e9d0e8ef73dc0 +size 667815456 diff --git a/128-goldfish-loss-llama-1B.Q4_K_S.gguf b/128-goldfish-loss-llama-1B.Q4_K_S.gguf new file mode 100644 index 0000000..9b11e8a --- /dev/null +++ b/128-goldfish-loss-llama-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0237bd0ba1b6b489815bbd8ab0619404b2e7baf178bb9829098e82811683384a +size 639872544 diff --git a/128-goldfish-loss-llama-1B.Q5_K_M.gguf b/128-goldfish-loss-llama-1B.Q5_K_M.gguf new file mode 100644 index 0000000..ff055f1 --- /dev/null +++ b/128-goldfish-loss-llama-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c6de4a6aa59387c06ed3e70b65578c6cd5d4cde920a59a2d13dc66fa4536fc +size 782044704 diff --git a/128-goldfish-loss-llama-1B.Q5_K_S.gguf b/128-goldfish-loss-llama-1B.Q5_K_S.gguf new file mode 100644 index 0000000..fa4123c --- /dev/null +++ b/128-goldfish-loss-llama-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4753cc69eaba619f96d014c85e396d3dd92e3d1c5b7598d986074c89c64eaf7 +size 766029344 diff --git a/128-goldfish-loss-llama-1B.Q6_K.gguf b/128-goldfish-loss-llama-1B.Q6_K.gguf new file mode 100644 index 0000000..076ddbb --- /dev/null +++ b/128-goldfish-loss-llama-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af9d8f12a63254b987c2a396dd0708af4b0d39e941179196ee9b7f2df3ca369 +size 903413280 diff --git a/128-goldfish-loss-llama-1B.Q8_0.gguf b/128-goldfish-loss-llama-1B.Q8_0.gguf new file mode 100644 index 0000000..79c97c1 --- /dev/null +++ b/128-goldfish-loss-llama-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50246711aa825451649bec47da352a721acc5ab4f1b2d0efae760fc943d89dc5 +size 1169808928 diff --git a/128-goldfish-loss-llama-1B.f16.gguf b/128-goldfish-loss-llama-1B.f16.gguf new file mode 100644 index 0000000..6692691 --- /dev/null +++ b/128-goldfish-loss-llama-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571613810c44ef3f8513eadb9c577cfebd55ba37bc10961a67d0bdb923fc4a4b +size 2201017888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..26ecf70 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: ahans1/128-goldfish-loss-llama-1B +datasets: +- tomg-group-umd/wikipedia-en-2k-samples +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- goldfish-loss +- memorization +- mitigation +--- +## About + + + + + + +static quants of https://huggingface.co/ahans1/128-goldfish-loss-llama-1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#128-goldfish-loss-llama-1B-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.IQ3_XS.gguf) | IQ3_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.IQ3_S.gguf) | IQ3_S | 0.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.IQ3_M.gguf) | IQ3_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/128-goldfish-loss-llama-1B-GGUF/resolve/main/128-goldfish-loss-llama-1B.f16.gguf) | f16 | 2.3 | 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. + +