commit e0dfa030bf8104ac600196e4575db4224c9c9d64 Author: ModelHub XC Date: Fri Sep 25 21:09:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PESTO-llama-base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..378c3e9 --- /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 +PESTO-llama-base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PESTO-llama-base.f16.gguf filter=lfs diff=lfs merge=lfs -text +PESTO-llama-base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PESTO-llama-base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PESTO-llama-base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PESTO-llama-base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PESTO-llama-base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PESTO-llama-base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PESTO-llama-base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PESTO-llama-base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PESTO-llama-base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PESTO-llama-base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PESTO-llama-base.IQ4_XS.gguf b/PESTO-llama-base.IQ4_XS.gguf new file mode 100644 index 0000000..1593649 --- /dev/null +++ b/PESTO-llama-base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8365e709aeb4d2ffb33f39958b8738295e5517340bdd6cd1cc860b2dcb95d3e9 +size 4484379328 diff --git a/PESTO-llama-base.Q2_K.gguf b/PESTO-llama-base.Q2_K.gguf new file mode 100644 index 0000000..07ce48b --- /dev/null +++ b/PESTO-llama-base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe61f24a103002cd760c9a9ab980b294302cb2e4f97ae4c31f45ea0fc572036d +size 3179146304 diff --git a/PESTO-llama-base.Q3_K_L.gguf b/PESTO-llama-base.Q3_K_L.gguf new file mode 100644 index 0000000..bad8d79 --- /dev/null +++ b/PESTO-llama-base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:276d383f5844c415327a478efe13c0a08ea5892afa43b2f4d5f44d81531d1714 +size 4321972096 diff --git a/PESTO-llama-base.Q3_K_M.gguf b/PESTO-llama-base.Q3_K_M.gguf new file mode 100644 index 0000000..c107791 --- /dev/null +++ b/PESTO-llama-base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad396a5b33b4e3624c996e81ee8e8aed17822e0a43080a0363e9b8635a621bd2 +size 4018933632 diff --git a/PESTO-llama-base.Q3_K_S.gguf b/PESTO-llama-base.Q3_K_S.gguf new file mode 100644 index 0000000..ee4760a --- /dev/null +++ b/PESTO-llama-base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e2efa79f9746edcd5b48fbdeeab8777c14ef4d24c2dbd8f9540574a1b98d3c6 +size 3664514944 diff --git a/PESTO-llama-base.Q4_K_M.gguf b/PESTO-llama-base.Q4_K_M.gguf new file mode 100644 index 0000000..cb8abee --- /dev/null +++ b/PESTO-llama-base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968a111c61ebe9cc1a18eafd3075bb5ebc420973871766d867596b72662b5a9c +size 4920751040 diff --git a/PESTO-llama-base.Q4_K_S.gguf b/PESTO-llama-base.Q4_K_S.gguf new file mode 100644 index 0000000..ed71d78 --- /dev/null +++ b/PESTO-llama-base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c14cadf34b05b5607d4b42f46fb10bfe1ac0443ee16c88237065447b21ad135b +size 4692685760 diff --git a/PESTO-llama-base.Q5_K_M.gguf b/PESTO-llama-base.Q5_K_M.gguf new file mode 100644 index 0000000..1bf4498 --- /dev/null +++ b/PESTO-llama-base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9880f1d1f7ac366192c586d35e5787bb26cc9e17bca226cf8283e2af101e99 +size 5733005248 diff --git a/PESTO-llama-base.Q5_K_S.gguf b/PESTO-llama-base.Q5_K_S.gguf new file mode 100644 index 0000000..006630d --- /dev/null +++ b/PESTO-llama-base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4658ac0456d3535ae46992794a74ac7a667c9e458bc24df4faf7b42695307a6a +size 5599311808 diff --git a/PESTO-llama-base.Q6_K.gguf b/PESTO-llama-base.Q6_K.gguf new file mode 100644 index 0000000..5a9fa92 --- /dev/null +++ b/PESTO-llama-base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:846a7db42eec0e97fe949f085b5087dc0db5afee60bd62d6f47535d163ccff38 +size 6596025344 diff --git a/PESTO-llama-base.Q8_0.gguf b/PESTO-llama-base.Q8_0.gguf new file mode 100644 index 0000000..acedf34 --- /dev/null +++ b/PESTO-llama-base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03027506250db218f6925adbc2f44418334f11944023467de185966cb85b9742 +size 8540793728 diff --git a/PESTO-llama-base.f16.gguf b/PESTO-llama-base.f16.gguf new file mode 100644 index 0000000..18aacfb --- /dev/null +++ b/PESTO-llama-base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9decd3d3aa30e674d124581918be7e8cfcae89405ef63d9765bb2877061b1f +size 16068929408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..846f747 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: jakeboggs/PESTO-llama-base +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/jakeboggs/PESTO-llama-base + + +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/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PESTO-llama-base-GGUF/resolve/main/PESTO-llama-base.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. + +