commit 5dc3f4bda4d9f37bd1193b708bb693fc522d09ec Author: ModelHub XC Date: Mon Sep 7 05:05:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e320985 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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-4-Layers_LoRA-PEFT-3.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_M.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_M.gguf new file mode 100644 index 0000000..65f5211 --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a51010298968a2a89f875d61ebe5679c150e83e70decf0ed6e746f3624ba9005 +size 3294350080 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_S.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_S.gguf new file mode 100644 index 0000000..e9ab48a --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b33f1ff63b8dc406f05e6ec9fa28939a5c5c53ac6ae9e3221d0176134d44c4 +size 3210791680 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_XS.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_XS.gguf new file mode 100644 index 0000000..56ffd5b --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1362f776252d945aac786128e795cc5b1abf9ba1cbbbd04bbd75ee2a33d17e41 +size 3074149120 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ4_XS.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ4_XS.gguf new file mode 100644 index 0000000..b390c42 --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175d8f2b8ba6cb02057d4d49e27193b46665b02f83c1364728b0f23f3a5b364d +size 3892407040 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q2_K.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q2_K.gguf new file mode 100644 index 0000000..52b999c --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47bd8f8ce66f6e8ed83ebf614655fca83f710e1b39d144de66b0f8d4e8caa2e1 +size 2777885440 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_L.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_L.gguf new file mode 100644 index 0000000..66ee8f1 --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c11452b2506158ab4ff650cebe6ea385ca0bba74e7d78592ead824f662f84d88 +size 3750480640 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_M.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_M.gguf new file mode 100644 index 0000000..e99f6c4 --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9324489376d6766afd1da87b45761396d521d36f454494be3a58563fbeb66fe4 +size 3489909504 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_S.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_S.gguf new file mode 100644 index 0000000..dafd14c --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c9827e1b7704c052fff868597cdbdea70f598c553984342e601126bb8b240ad +size 3195751168 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q4_K_M.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q4_K_M.gguf new file mode 100644 index 0000000..539567c --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3be99e402ed57be8261bba94d6a7185fc5d9b4ef1530e502d82df0afe7f05ae +size 4258491136 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q4_K_S.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q4_K_S.gguf new file mode 100644 index 0000000..03abb37 --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e2031d13f281ef80b09676ef5578a1eb21af90e58640ea775d3c3164cc721aa +size 4071746304 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q5_K_M.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q5_K_M.gguf new file mode 100644 index 0000000..317877c --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c76fe74094b2e1c84bc01652433d3d12c3980960ec09fabb8aef7db8228afcf +size 4958022400 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q5_K_S.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q5_K_S.gguf new file mode 100644 index 0000000..6244d45 --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d94c1ed01320d26e9203b51cf83f61b196cfce026b78869917a691a696b9a8 +size 4849396480 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q6_K.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q6_K.gguf new file mode 100644 index 0000000..de92e70 --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba54500e48a4a6effdbae7d6adef7c21d2c3497fdbf41975f700c27f238a2b4c +size 5701274368 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q8_0.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q8_0.gguf new file mode 100644 index 0000000..cbeb8c8 --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b722dc834d46282f30f952703c76981cb2c2c2256405a785ea3412ca61b18af +size 7381928704 diff --git a/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.f16.gguf b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.f16.gguf new file mode 100644 index 0000000..821c9f9 --- /dev/null +++ b/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a014c8b5a7dd69555508393cac843d57e5b3a2495c57985ea14121de5f05a2b +size 13887687424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..47e8ef4 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0 +datasets: +- teknium/openhermes +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-i1-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-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q2_K.gguf) | Q2_K | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_XS.gguf) | IQ3_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q4_K_M.gguf) | Q4_K_M | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q5_K_S.gguf) | Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q5_K_M.gguf) | Q5_K_M | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q6_K.gguf) | Q6_K | 5.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.Q8_0.gguf) | Q8_0 | 7.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUF/resolve/main/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0.f16.gguf) | f16 | 14.0 | 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. + +