commit 0e7dab2a6c2c2362e1ecd91d89fbc7eb5b390c6e Author: ModelHub XC Date: Sat Jun 13 03:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6c3de89 --- /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-3.1-8b-Pruned-2-Layers.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-Pruned-2-Layers.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8b-Pruned-2-Layers.IQ3_M.gguf b/Llama-3.1-8b-Pruned-2-Layers.IQ3_M.gguf new file mode 100644 index 0000000..cd53f89 --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b080e03f65a32e9239ea8c8e7f70669ca1c92d59d823d4c7eb7619cf8aad54 +size 3487419968 diff --git a/Llama-3.1-8b-Pruned-2-Layers.IQ3_S.gguf b/Llama-3.1-8b-Pruned-2-Layers.IQ3_S.gguf new file mode 100644 index 0000000..c521d2f --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3bae89b46e8990a6c88e26e613b06b39465c3ca6fa32771e62742bfa183617 +size 3399405120 diff --git a/Llama-3.1-8b-Pruned-2-Layers.IQ3_XS.gguf b/Llama-3.1-8b-Pruned-2-Layers.IQ3_XS.gguf new file mode 100644 index 0000000..28615c6 --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2ec1c0a6556dcfdada346cd27392d344d4ae0d45ec61aa5113d45e8f8f500a1 +size 3249786432 diff --git a/Llama-3.1-8b-Pruned-2-Layers.IQ4_XS.gguf b/Llama-3.1-8b-Pruned-2-Layers.IQ4_XS.gguf new file mode 100644 index 0000000..4455a22 --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734330fa8a8d5a446c354058a9376df5a714685ebdda08c144db31f7bb41e710 +size 4125519424 diff --git a/Llama-3.1-8b-Pruned-2-Layers.Q2_K.gguf b/Llama-3.1-8b-Pruned-2-Layers.Q2_K.gguf new file mode 100644 index 0000000..682fa18 --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed429106e74f178ec983cc9af9be2aab0dda464d3ad614e613a24faf2d5a9e07 +size 2938383936 diff --git a/Llama-3.1-8b-Pruned-2-Layers.Q3_K_L.gguf b/Llama-3.1-8b-Pruned-2-Layers.Q3_K_L.gguf new file mode 100644 index 0000000..71e1ed5 --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ab15741f391be8fee1ffbc1a5ab33e40cc9242b3b16785c2d897e7d243401a +size 3979071040 diff --git a/Llama-3.1-8b-Pruned-2-Layers.Q3_K_M.gguf b/Llama-3.1-8b-Pruned-2-Layers.Q3_K_M.gguf new file mode 100644 index 0000000..e801d41 --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bebf68bfd1912b09eb4f89bd638d2b8e1dab9cfc4a385ec7f7f7083b9ac6f80 +size 3698576960 diff --git a/Llama-3.1-8b-Pruned-2-Layers.Q3_K_S.gguf b/Llama-3.1-8b-Pruned-2-Layers.Q3_K_S.gguf new file mode 100644 index 0000000..0d35389 --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1e1214f65f3c302f52b2ab26e78db506bcb16abc5ac9f9f1e0481f8ece437fe +size 3383250496 diff --git a/Llama-3.1-8b-Pruned-2-Layers.Q4_K_M.gguf b/Llama-3.1-8b-Pruned-2-Layers.Q4_K_M.gguf new file mode 100644 index 0000000..2557da1 --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06762e99426029c60821ad0a9e3914e48527eb0ca44f17ac49028842dd91edc2 +size 4520144448 diff --git a/Llama-3.1-8b-Pruned-2-Layers.Q4_K_S.gguf b/Llama-3.1-8b-Pruned-2-Layers.Q4_K_S.gguf new file mode 100644 index 0000000..94cc487 --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9619fcf1ac0fd11a4f5453a35564aefee3574e82eb9d9d8bf2ac682c4e9a9fce +size 4317179456 diff --git a/Llama-3.1-8b-Pruned-2-Layers.Q5_K_M.gguf b/Llama-3.1-8b-Pruned-2-Layers.Q5_K_M.gguf new file mode 100644 index 0000000..b9ffcf3 --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8eb96dd47b1f143b6b78ae65b95a7c8dd02bde7d0445bcee580dbbfb2a2a48c +size 5266337344 diff --git a/Llama-3.1-8b-Pruned-2-Layers.Q5_K_S.gguf b/Llama-3.1-8b-Pruned-2-Layers.Q5_K_S.gguf new file mode 100644 index 0000000..50499cc --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e7ffdbd630cc40941c313562ccac59a431e96c108aaebe52a61c4d6bf59ba9 +size 5149355584 diff --git a/Llama-3.1-8b-Pruned-2-Layers.Q6_K.gguf b/Llama-3.1-8b-Pruned-2-Layers.Q6_K.gguf new file mode 100644 index 0000000..aa50e03 --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa488fc2b7f211ccf4e1610e190f6b4369d21a4036d1da94362c89385f12dbdf +size 6059167296 diff --git a/Llama-3.1-8b-Pruned-2-Layers.Q8_0.gguf b/Llama-3.1-8b-Pruned-2-Layers.Q8_0.gguf new file mode 100644 index 0000000..b28299d --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2897a461b1f955d095b1602d95a515ee508c38ec68cb86171e5c842eb6bce5e3 +size 7845465664 diff --git a/Llama-3.1-8b-Pruned-2-Layers.f16.gguf b/Llama-3.1-8b-Pruned-2-Layers.f16.gguf new file mode 100644 index 0000000..c5b3d4e --- /dev/null +++ b/Llama-3.1-8b-Pruned-2-Layers.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1236cad019fd98aa079beb325a9cee27f237a3bbc40531f3c0caa4de6f401a +size 14760169024 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3fa5ef5 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Na0s/Llama-3.1-8b-Pruned-2-Layers +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Na0s/Llama-3.1-8b-Pruned-2-Layers + + +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-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.Q2_K.gguf) | Q2_K | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.IQ3_XS.gguf) | IQ3_XS | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.Q3_K_S.gguf) | Q3_K_S | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.IQ3_S.gguf) | IQ3_S | 3.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.IQ3_M.gguf) | IQ3_M | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.Q3_K_L.gguf) | Q3_K_L | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.IQ4_XS.gguf) | IQ4_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.Q5_K_S.gguf) | Q5_K_S | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.Q5_K_M.gguf) | Q5_K_M | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.Q6_K.gguf) | Q6_K | 6.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-Pruned-2-Layers-GGUF/resolve/main/Llama-3.1-8b-Pruned-2-Layers.f16.gguf) | f16 | 14.9 | 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. + +