commit 34bcea10611e4c65a30c751e1c3564933e5b7ef8 Author: ModelHub XC Date: Tue Jun 16 10:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-lima-nsfw-16k-test-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a75cb26 --- /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 +Llama-3-lima-nsfw-16k-test.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-lima-nsfw-16k-test.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-lima-nsfw-16k-test.IQ3_M.gguf b/Llama-3-lima-nsfw-16k-test.IQ3_M.gguf new file mode 100644 index 0000000..1d41c21 --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:856baeb45eb221d25e14d7712a7ed269edc110d0a395c54982d8110da3153697 +size 3784844192 diff --git a/Llama-3-lima-nsfw-16k-test.IQ3_S.gguf b/Llama-3-lima-nsfw-16k-test.IQ3_S.gguf new file mode 100644 index 0000000..0a860db --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddc2de9da926352e9a8c2224e92f68ea3bdc63a2e23f2c45320e4c63333d6695 +size 3682345888 diff --git a/Llama-3-lima-nsfw-16k-test.IQ3_XS.gguf b/Llama-3-lima-nsfw-16k-test.IQ3_XS.gguf new file mode 100644 index 0000000..1da202e --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccfa587087ba241b0521498d461261b27159f12f055bbeefdda917e8fe43a1ab +size 3518768032 diff --git a/Llama-3-lima-nsfw-16k-test.IQ4_XS.gguf b/Llama-3-lima-nsfw-16k-test.IQ4_XS.gguf new file mode 100644 index 0000000..777c25a --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d5fd192f2472baa057d6e1468fdc96d03346476537f0503428a5b48417a0433 +size 4484385312 diff --git a/Llama-3-lima-nsfw-16k-test.Q2_K.gguf b/Llama-3-lima-nsfw-16k-test.Q2_K.gguf new file mode 100644 index 0000000..70580be --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e14990c045df95bf1385b61572be108ddfa736a5f9d9c605a393ffb965b6c470 +size 3179150624 diff --git a/Llama-3-lima-nsfw-16k-test.Q3_K_L.gguf b/Llama-3-lima-nsfw-16k-test.Q3_K_L.gguf new file mode 100644 index 0000000..7f9271f --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80d859e1c79fdb876bd146c4c646818dd62035c542b28d4e353f8bb01bc3a291 +size 4321977248 diff --git a/Llama-3-lima-nsfw-16k-test.Q3_K_M.gguf b/Llama-3-lima-nsfw-16k-test.Q3_K_M.gguf new file mode 100644 index 0000000..a1b4457 --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8950ba6adc1625c7e4f56aaaf4d529a695f7d14aeac024004369164ef72a955 +size 4018938784 diff --git a/Llama-3-lima-nsfw-16k-test.Q3_K_S.gguf b/Llama-3-lima-nsfw-16k-test.Q3_K_S.gguf new file mode 100644 index 0000000..0b3c575 --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12979c1796971ec9917697279b0b1f65772034c581e22ee4b661baf0c63647d4 +size 3664520096 diff --git a/Llama-3-lima-nsfw-16k-test.Q4_K_M.gguf b/Llama-3-lima-nsfw-16k-test.Q4_K_M.gguf new file mode 100644 index 0000000..bd3ba95 --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f519934d34c17293ecf296a3c70eb7e2865f38cf6e36f29f51e435ad48efc3d2 +size 4920757280 diff --git a/Llama-3-lima-nsfw-16k-test.Q4_K_S.gguf b/Llama-3-lima-nsfw-16k-test.Q4_K_S.gguf new file mode 100644 index 0000000..dcd2a2c --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b1d5e8c555fbdd85ecf8ff203f8e887a53bf9a09f5dbdd3f70484ab6a537765 +size 4692692000 diff --git a/Llama-3-lima-nsfw-16k-test.Q5_K_M.gguf b/Llama-3-lima-nsfw-16k-test.Q5_K_M.gguf new file mode 100644 index 0000000..9ad81ae --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:640f4bfdc5890fff82b16eeef303ca57bf0d99c9b993ea937ebfe5b84a8e0b50 +size 5733012512 diff --git a/Llama-3-lima-nsfw-16k-test.Q5_K_S.gguf b/Llama-3-lima-nsfw-16k-test.Q5_K_S.gguf new file mode 100644 index 0000000..fe50a23 --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a0c73bd4512172f005a7a8091b1fe161b182bc533a8574793c4162dbc3e4ac1 +size 5599319072 diff --git a/Llama-3-lima-nsfw-16k-test.Q6_K.gguf b/Llama-3-lima-nsfw-16k-test.Q6_K.gguf new file mode 100644 index 0000000..2602f58 --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a11eaa1adb908ab31e8e00a1ba0ac3f02ef90696668bafd61f917ef4c8e52563 +size 6596033696 diff --git a/Llama-3-lima-nsfw-16k-test.Q8_0.gguf b/Llama-3-lima-nsfw-16k-test.Q8_0.gguf new file mode 100644 index 0000000..c0a1827 --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a5d1161bcdf0718040659289802e6820bdec8a3c4c930cfc776b9c9c30b5091 +size 8540806048 diff --git a/Llama-3-lima-nsfw-16k-test.f16.gguf b/Llama-3-lima-nsfw-16k-test.f16.gguf new file mode 100644 index 0000000..6884790 --- /dev/null +++ b/Llama-3-lima-nsfw-16k-test.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f671e51e459ece9fc14318bdfd2ecbac576976893d0eb364cd8e1dc99b4715c +size 16068957088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..30d1856 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: openerotica/Llama-3-lima-nsfw-16k-test +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/openerotica/Llama-3-lima-nsfw-16k-test + + +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/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-lima-nsfw-16k-test-GGUF/resolve/main/Llama-3-lima-nsfw-16k-test.f16.gguf) | f16 | 16.2 | 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. + +