commit dcc8f5fc50f2610b38fc434b1068b7e5e31a8afd Author: ModelHub XC Date: Thu Jul 30 13:33:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-mawared-2E-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dd9ad0e --- /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 +llama3-mawared-2E.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3-mawared-2E.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3faebf5 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Ammartatox/llama3-mawared-2E +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/Ammartatox/llama3-mawared-2E + + +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/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-mawared-2E-GGUF/resolve/main/llama3-mawared-2E.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. + + diff --git a/llama3-mawared-2E.IQ3_M.gguf b/llama3-mawared-2E.IQ3_M.gguf new file mode 100644 index 0000000..83fecfd --- /dev/null +++ b/llama3-mawared-2E.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3651adad2ca037121b6e140935468bdfb7f058403c4eb99e7486f325e593014b +size 3784823552 diff --git a/llama3-mawared-2E.IQ3_S.gguf b/llama3-mawared-2E.IQ3_S.gguf new file mode 100644 index 0000000..960c0fe --- /dev/null +++ b/llama3-mawared-2E.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2039d98fc217c677cfd54af9a96d8eadda8f065e195c12ace4959dd4e3c357a5 +size 3682325248 diff --git a/llama3-mawared-2E.IQ3_XS.gguf b/llama3-mawared-2E.IQ3_XS.gguf new file mode 100644 index 0000000..e7a47ce --- /dev/null +++ b/llama3-mawared-2E.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9afaffa2d869e8850378209b8323b1f7e6094ed7b50b689c148beabcc83cc633 +size 3518747392 diff --git a/llama3-mawared-2E.IQ4_XS.gguf b/llama3-mawared-2E.IQ4_XS.gguf new file mode 100644 index 0000000..f986e2b --- /dev/null +++ b/llama3-mawared-2E.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44e752f25e1eeaf75e1ae253b0676845fc9ba40d4250130f7fa2495fb16b3e7 +size 4484363008 diff --git a/llama3-mawared-2E.Q2_K.gguf b/llama3-mawared-2E.Q2_K.gguf new file mode 100644 index 0000000..a36bcac --- /dev/null +++ b/llama3-mawared-2E.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39c0b968e9dd45f6b3adefede36e7ddb2517b9134ed17d7c726596c80526cd21 +size 3179131648 diff --git a/llama3-mawared-2E.Q3_K_L.gguf b/llama3-mawared-2E.Q3_K_L.gguf new file mode 100644 index 0000000..13d0a05 --- /dev/null +++ b/llama3-mawared-2E.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a944fe7ceb97ab633e1b3b8424595d5a5e523c91d9354c18e6599bdc48733fd6 +size 4321956608 diff --git a/llama3-mawared-2E.Q3_K_M.gguf b/llama3-mawared-2E.Q3_K_M.gguf new file mode 100644 index 0000000..6dc6929 --- /dev/null +++ b/llama3-mawared-2E.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c7102f889be056d8f674770e9c27871c781c7ad47e96312b2ac0c32209e50bc +size 4018918144 diff --git a/llama3-mawared-2E.Q3_K_S.gguf b/llama3-mawared-2E.Q3_K_S.gguf new file mode 100644 index 0000000..5eeea24 --- /dev/null +++ b/llama3-mawared-2E.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a3313434e822fae616ddb8876c0e6dda92f905a3a4f4fa41c512186f7475135 +size 3664499456 diff --git a/llama3-mawared-2E.Q4_K_M.gguf b/llama3-mawared-2E.Q4_K_M.gguf new file mode 100644 index 0000000..8a22792 --- /dev/null +++ b/llama3-mawared-2E.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f66db0a7bcaad97e884c9e59588a5699cadce70ad8407a0326cd1a44b1a73713 +size 4920734464 diff --git a/llama3-mawared-2E.Q4_K_S.gguf b/llama3-mawared-2E.Q4_K_S.gguf new file mode 100644 index 0000000..cd153c0 --- /dev/null +++ b/llama3-mawared-2E.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:332ccd4fe585762abcbec52763a52dfa18c1a422e1642344fcf33f540d006dd2 +size 4692669184 diff --git a/llama3-mawared-2E.Q5_K_M.gguf b/llama3-mawared-2E.Q5_K_M.gguf new file mode 100644 index 0000000..06b5bf7 --- /dev/null +++ b/llama3-mawared-2E.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44b8eeba3de8806d288e5d267c09dd890b5dd699bc543973f12192e7a0c260cf +size 5732987648 diff --git a/llama3-mawared-2E.Q5_K_S.gguf b/llama3-mawared-2E.Q5_K_S.gguf new file mode 100644 index 0000000..57de53a --- /dev/null +++ b/llama3-mawared-2E.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dfa2136d832b81784071fb957af59aa01d642101f6455a96d814f4038033eb5 +size 5599294208 diff --git a/llama3-mawared-2E.Q6_K.gguf b/llama3-mawared-2E.Q6_K.gguf new file mode 100644 index 0000000..a7adf93 --- /dev/null +++ b/llama3-mawared-2E.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3768d18de7a96fea90905f44c17c8fb57f96b7f89db6c2d5dd9844aa123a67c8 +size 6596006656 diff --git a/llama3-mawared-2E.Q8_0.gguf b/llama3-mawared-2E.Q8_0.gguf new file mode 100644 index 0000000..49fd6d1 --- /dev/null +++ b/llama3-mawared-2E.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4abc852d5277b550718964d18b478c47a0a6d46d59ea9fc52a89d931c57cf95 +size 8540771072 diff --git a/llama3-mawared-2E.f16.gguf b/llama3-mawared-2E.f16.gguf new file mode 100644 index 0000000..30caefb --- /dev/null +++ b/llama3-mawared-2E.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5026c841ee72dddf49332884e73f22aac4700f58b915bac77c428c873afc1467 +size 16068891392