commit f9b6aaa9e9d8175acbddef1deaeb526163263cec Author: ModelHub XC Date: Tue Sep 29 00:39:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Minus-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bf36b7b --- /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 +Llama-3-Minus-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Minus-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Minus-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Minus-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Minus-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Minus-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Minus-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Minus-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Minus-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Minus-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Minus-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Minus-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Minus-Base.IQ4_XS.gguf b/Llama-3-Minus-Base.IQ4_XS.gguf new file mode 100644 index 0000000..f320363 --- /dev/null +++ b/Llama-3-Minus-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3721222b86c1d36af6088dbe6a0129e33e928954e7a5fbe5cbf8858abf8c6fe +size 4484363232 diff --git a/Llama-3-Minus-Base.Q2_K.gguf b/Llama-3-Minus-Base.Q2_K.gguf new file mode 100644 index 0000000..068abf5 --- /dev/null +++ b/Llama-3-Minus-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5750b18c13dbc1bf1109df3bcc5f1bd51407d6e55716bbfaf469319deae001f7 +size 3179131872 diff --git a/Llama-3-Minus-Base.Q3_K_L.gguf b/Llama-3-Minus-Base.Q3_K_L.gguf new file mode 100644 index 0000000..7f1bc7c --- /dev/null +++ b/Llama-3-Minus-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1c4c9709d17642cd24658dadc23ca0917a61d75ce4c3d1441d0edf0c9c4de04 +size 4321956832 diff --git a/Llama-3-Minus-Base.Q3_K_M.gguf b/Llama-3-Minus-Base.Q3_K_M.gguf new file mode 100644 index 0000000..9e15d13 --- /dev/null +++ b/Llama-3-Minus-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6b4a2332b34bdc7cb2ca1f6411350528788b6da409d6beb2a0b7636877cd2a4 +size 4018918368 diff --git a/Llama-3-Minus-Base.Q3_K_S.gguf b/Llama-3-Minus-Base.Q3_K_S.gguf new file mode 100644 index 0000000..d397464 --- /dev/null +++ b/Llama-3-Minus-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7959834aadfbe27af2888a3351de6d01c1098cc1b3e7de9a340c6f48f95fd3be +size 3664499680 diff --git a/Llama-3-Minus-Base.Q4_K_M.gguf b/Llama-3-Minus-Base.Q4_K_M.gguf new file mode 100644 index 0000000..9aef045 --- /dev/null +++ b/Llama-3-Minus-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:893f4aa9838a1518a7b8cbb276f62e7bf109a32477d1678ed8d2012b9654bfe6 +size 4920734688 diff --git a/Llama-3-Minus-Base.Q4_K_S.gguf b/Llama-3-Minus-Base.Q4_K_S.gguf new file mode 100644 index 0000000..0918976 --- /dev/null +++ b/Llama-3-Minus-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd8f04ddba2e676c33b4fcdd2405ab2e41efe946972483b8ca13cb83bc2d2e41 +size 4692669408 diff --git a/Llama-3-Minus-Base.Q5_K_M.gguf b/Llama-3-Minus-Base.Q5_K_M.gguf new file mode 100644 index 0000000..06f4abc --- /dev/null +++ b/Llama-3-Minus-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bf3729b4e04d5464be2977ae0da7f61917a25b221b67ae561c387479388a2e7 +size 5732987872 diff --git a/Llama-3-Minus-Base.Q5_K_S.gguf b/Llama-3-Minus-Base.Q5_K_S.gguf new file mode 100644 index 0000000..1789e5d --- /dev/null +++ b/Llama-3-Minus-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c48c71463517273f5abe56a754eb18c7400a31108de05faa1bc9a396ea8f149 +size 5599294432 diff --git a/Llama-3-Minus-Base.Q6_K.gguf b/Llama-3-Minus-Base.Q6_K.gguf new file mode 100644 index 0000000..89e6299 --- /dev/null +++ b/Llama-3-Minus-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9668dff42741127d418e20dfe7e53f2dc6386990cd9ce2f1644bf6e5d06a5d0 +size 6596006880 diff --git a/Llama-3-Minus-Base.Q8_0.gguf b/Llama-3-Minus-Base.Q8_0.gguf new file mode 100644 index 0000000..7ae4e3d --- /dev/null +++ b/Llama-3-Minus-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:073c432b83249626e93122f7ec0e34e5c0626caf8e5f6ee9afc9e1eaa8c7b9a6 +size 8540771296 diff --git a/Llama-3-Minus-Base.f16.gguf b/Llama-3-Minus-Base.f16.gguf new file mode 100644 index 0000000..d97a93b --- /dev/null +++ b/Llama-3-Minus-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a470327fcb51b1f6bfe71ef35ce26f497cfdc57b07f0773182af45cc7d5feeb8 +size 16068891616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..268850a --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Cas-Warehouse/Llama-3-Minus-Base +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Cas-Warehouse/Llama-3-Minus-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/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-Base.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-Base.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-Base.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-Base.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-Base.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-Base.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-Base.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-Base.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-Base.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-Base.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-Base.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Minus-Base-GGUF/resolve/main/Llama-3-Minus-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. + +