commit c33e03938b36e44451c0bdd6b5c57863e1f2d022 Author: ModelHub XC Date: Mon Sep 7 05:29:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dc0ad67 --- /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 +LLama3-8B-CraftaxClassic-LoRa.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLama3-8B-CraftaxClassic-LoRa.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLama3-8B-CraftaxClassic-LoRa.IQ3_M.gguf b/LLama3-8B-CraftaxClassic-LoRa.IQ3_M.gguf new file mode 100644 index 0000000..7fa93e2 --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e90cd64411ec4551e6f26677d869d733c36b0c698a8b203bd6a09b548c417a63 +size 3784824000 diff --git a/LLama3-8B-CraftaxClassic-LoRa.IQ3_S.gguf b/LLama3-8B-CraftaxClassic-LoRa.IQ3_S.gguf new file mode 100644 index 0000000..cae52ea --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d84a28367bc46dce849e2a7f1ca18b8196c5ddfb511d818098d797f5cb3578e1 +size 3682325696 diff --git a/LLama3-8B-CraftaxClassic-LoRa.IQ3_XS.gguf b/LLama3-8B-CraftaxClassic-LoRa.IQ3_XS.gguf new file mode 100644 index 0000000..bcd5fa7 --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b87e99bfeecfcda4e20eea47c09da8fb3b01b86d4efb1a704462cd8da1c7c07a +size 3518747840 diff --git a/LLama3-8B-CraftaxClassic-LoRa.IQ4_XS.gguf b/LLama3-8B-CraftaxClassic-LoRa.IQ4_XS.gguf new file mode 100644 index 0000000..f5b372a --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584970da8d004afa65dc61f070270bda2675e7f97f57c56e6991898dc81ba2b6 +size 4484363456 diff --git a/LLama3-8B-CraftaxClassic-LoRa.Q2_K.gguf b/LLama3-8B-CraftaxClassic-LoRa.Q2_K.gguf new file mode 100644 index 0000000..44fecfe --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb5f582b4682c000d4d6dae6baa169ab218f810229f130db939bdca6a3b55941 +size 3179132096 diff --git a/LLama3-8B-CraftaxClassic-LoRa.Q3_K_L.gguf b/LLama3-8B-CraftaxClassic-LoRa.Q3_K_L.gguf new file mode 100644 index 0000000..0b70890 --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2effa6889e6d4f58244dc3be0eb118ffb872e4998e5217bc44b4c0b279fc9d86 +size 4321957056 diff --git a/LLama3-8B-CraftaxClassic-LoRa.Q3_K_M.gguf b/LLama3-8B-CraftaxClassic-LoRa.Q3_K_M.gguf new file mode 100644 index 0000000..6d87ed2 --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0079b0b405cdbae4e7d3870e1b97b86622a961f71d8e965430b73bf9a8091bd1 +size 4018918592 diff --git a/LLama3-8B-CraftaxClassic-LoRa.Q3_K_S.gguf b/LLama3-8B-CraftaxClassic-LoRa.Q3_K_S.gguf new file mode 100644 index 0000000..d254792 --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b090b3e78669df6ad3b4411f3594ff9cc197dfd2fa1c954ad5897b70decb65b6 +size 3664499904 diff --git a/LLama3-8B-CraftaxClassic-LoRa.Q4_K_M.gguf b/LLama3-8B-CraftaxClassic-LoRa.Q4_K_M.gguf new file mode 100644 index 0000000..cddc322 --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b42a9b21c9cf901fb70fa99b10fcb79a90444be6e0df6855f9163f94d935574f +size 4920734912 diff --git a/LLama3-8B-CraftaxClassic-LoRa.Q4_K_S.gguf b/LLama3-8B-CraftaxClassic-LoRa.Q4_K_S.gguf new file mode 100644 index 0000000..9318d3d --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c183650917cdfce5109a74174b659dfd180805b04c30ef551ebc96d7974b1e +size 4692669632 diff --git a/LLama3-8B-CraftaxClassic-LoRa.Q5_K_M.gguf b/LLama3-8B-CraftaxClassic-LoRa.Q5_K_M.gguf new file mode 100644 index 0000000..18080c7 --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a626533d5f82ae97d860cac9be0c814c9b8df01be6bc549150e08e640d12b5a +size 5732988096 diff --git a/LLama3-8B-CraftaxClassic-LoRa.Q5_K_S.gguf b/LLama3-8B-CraftaxClassic-LoRa.Q5_K_S.gguf new file mode 100644 index 0000000..2d63e3b --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb67b71e3c8f5632f3a01839e33cdd54b7cf7fa02f0f6a70326649c53f81684d +size 5599294656 diff --git a/LLama3-8B-CraftaxClassic-LoRa.Q6_K.gguf b/LLama3-8B-CraftaxClassic-LoRa.Q6_K.gguf new file mode 100644 index 0000000..ca455bc --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:787e67a8ac91d68d449ff4767d225d1c36138c1b9710d29a4f999238229d0598 +size 6596007104 diff --git a/LLama3-8B-CraftaxClassic-LoRa.Q8_0.gguf b/LLama3-8B-CraftaxClassic-LoRa.Q8_0.gguf new file mode 100644 index 0000000..4bd6e4e --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e71cd0bc08513bd099ea890db3d922c1de63d9d25dd90cf5a5ba05ad2e977f64 +size 8540771520 diff --git a/LLama3-8B-CraftaxClassic-LoRa.f16.gguf b/LLama3-8B-CraftaxClassic-LoRa.f16.gguf new file mode 100644 index 0000000..3998eff --- /dev/null +++ b/LLama3-8B-CraftaxClassic-LoRa.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32ff58c5e747efca7a764c9c748226f9a61824a6deb0f66a119bdae59525d023 +size 16068891840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7661e41 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: rogercc/LLama3-8B-CraftaxClassic-LoRa +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/rogercc/LLama3-8B-CraftaxClassic-LoRa + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-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/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLama3-8B-CraftaxClassic-LoRa-GGUF/resolve/main/LLama3-8B-CraftaxClassic-LoRa.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. + +