commit a1dc44c8a4062a4e4cb59192cb8a80277f685b9d Author: ModelHub XC Date: Wed Jun 17 17:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-LiPPA-8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..30c774c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,56 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-LiPPA-8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-LiPPA-8B.i1-IQ1_M.gguf b/Llama-3-LiPPA-8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..ebaaf01 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ff5e1da3399a09c0585722cb34d7a60ba655d2562ea17658aba23d7c4c275c +size 2161972224 diff --git a/Llama-3-LiPPA-8B.i1-IQ1_S.gguf b/Llama-3-LiPPA-8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..bb24039 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441ef9245815e7846a1b965a497dd3bdace147dc0f466ab24102f3b9760c41a8 +size 2019628032 diff --git a/Llama-3-LiPPA-8B.i1-IQ2_M.gguf b/Llama-3-LiPPA-8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..3cdc829 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc6f7abf10138a367f0826623580c959eb6af08bf1b74bd888439bd13bddadb0 +size 2948281344 diff --git a/Llama-3-LiPPA-8B.i1-IQ2_S.gguf b/Llama-3-LiPPA-8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..ad53029 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:800ef3e586b2a95c1d1eb7434999bf473ddb66990c9255838916362628643906 +size 2758489088 diff --git a/Llama-3-LiPPA-8B.i1-IQ2_XS.gguf b/Llama-3-LiPPA-8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..f68970f --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2065988e3db2d455df5f48b2cd11bbf5bebbbb828c664df25c5602704d03c2e1 +size 2605782016 diff --git a/Llama-3-LiPPA-8B.i1-IQ2_XXS.gguf b/Llama-3-LiPPA-8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..484d179 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657dabd3185fd61a550c4636df4c5eccbb515492a3520c22f2bb262fef0dcf03 +size 2399212544 diff --git a/Llama-3-LiPPA-8B.i1-IQ3_M.gguf b/Llama-3-LiPPA-8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..0843260 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6a4e9a5eb0e4d749ff6162c92fc9d30f20749189b0c2940ada496b87a39ac9a +size 3784823808 diff --git a/Llama-3-LiPPA-8B.i1-IQ3_S.gguf b/Llama-3-LiPPA-8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..8587e62 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bc49a6d99103b01180e366fa52423924b18747d6b4e3d7140e987465207c1df +size 3682325504 diff --git a/Llama-3-LiPPA-8B.i1-IQ3_XS.gguf b/Llama-3-LiPPA-8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2848f80 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7712fa32672901c3d1db235e21dc6a5c90c4919bd4575a8a73877296a0b65c2f +size 3518747648 diff --git a/Llama-3-LiPPA-8B.i1-IQ3_XXS.gguf b/Llama-3-LiPPA-8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..23310e2 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08154821287b5a874287357dd5d791a5b1d298091913bc31764203d1b733cb27 +size 3274912768 diff --git a/Llama-3-LiPPA-8B.i1-IQ4_XS.gguf b/Llama-3-LiPPA-8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..15370da --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e25dd222a0c7165b80adb6e0406e74270f0c8c5ef299a7da911bb91ae731991a +size 4447663104 diff --git a/Llama-3-LiPPA-8B.i1-Q2_K.gguf b/Llama-3-LiPPA-8B.i1-Q2_K.gguf new file mode 100644 index 0000000..a8df426 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f82ae4c0f44723f36c090ac4591a490f3b965a21e5c5eb7a7e2fbcd087bf7926 +size 3179131904 diff --git a/Llama-3-LiPPA-8B.i1-Q3_K_L.gguf b/Llama-3-LiPPA-8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..cfc954a --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fde0a389242122c917a6755d058d4a4bd961e6a8f7d91f76d99c150181702e2a +size 4321956864 diff --git a/Llama-3-LiPPA-8B.i1-Q3_K_M.gguf b/Llama-3-LiPPA-8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1f254da --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59381d3c33c230d5751ecf4f53ffe34bb9147f45b89dd7bad4aa99dbee182c9b +size 4018918400 diff --git a/Llama-3-LiPPA-8B.i1-Q3_K_S.gguf b/Llama-3-LiPPA-8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..0e27604 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b79abef653e531b66f0376a8b03819c62924a53f9930737a908cf939e6fdc93b +size 3664499712 diff --git a/Llama-3-LiPPA-8B.i1-Q4_0.gguf b/Llama-3-LiPPA-8B.i1-Q4_0.gguf new file mode 100644 index 0000000..466dd17 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c81d5b077da673a38f9a8ba6312f6fe5b5f2689b9d2ec9e390e7546ac3bb320a +size 4675892224 diff --git a/Llama-3-LiPPA-8B.i1-Q4_K_M.gguf b/Llama-3-LiPPA-8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..10b9c5c --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48c83338a8f102d75b613711811b51d5e3a2400fa274fb2b739133d62b8d9109 +size 4920734720 diff --git a/Llama-3-LiPPA-8B.i1-Q4_K_S.gguf b/Llama-3-LiPPA-8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..deaf62f --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5449d28b155f992b294bd93e623a8c7ca25761aa945a0657cb61c6e43a5f64ed +size 4692669440 diff --git a/Llama-3-LiPPA-8B.i1-Q5_K_M.gguf b/Llama-3-LiPPA-8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..63d36b7 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d8550558e203ea566716b741d54a1cb47b8fcabffe0d2d22e9e2cd91579e85 +size 5732987904 diff --git a/Llama-3-LiPPA-8B.i1-Q5_K_S.gguf b/Llama-3-LiPPA-8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..68efae2 --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e806aa51a533965030a657e5eea009b6f499dc5532113ccaa9c5a51fc0f447a +size 5599294464 diff --git a/Llama-3-LiPPA-8B.i1-Q6_K.gguf b/Llama-3-LiPPA-8B.i1-Q6_K.gguf new file mode 100644 index 0000000..28ab5ed --- /dev/null +++ b/Llama-3-LiPPA-8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d345be55f11d3e2637321734db19b65db693ec09beead7c08911fba56d2b2ac2 +size 6596006912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a533cab --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: mpasila/Llama-3-LiPPA-8B +datasets: +- mpasila/LimaRP-PIPPA-Mix-8K-Context +- grimulkan/LimaRP-augmented +- KaraKaraWitch/PIPPA-ShareGPT-formatted +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +- not-for-all-audiences +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/mpasila/Llama-3-LiPPA-8B + + +static quants are available at https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-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/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-LiPPA-8B-i1-GGUF/resolve/main/Llama-3-LiPPA-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..d7ddfa0 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daa6b0a770d18adbbbe2b03c5f87bce0f86ec95dfdf45704c319d25a0c014ac4 +size 4988161