commit 91d05566acf5ca84b276650ab41740cd048c3511 Author: ModelHub XC Date: Sun Aug 9 08:35:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-Sophie-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..916dccf --- /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-Sophie.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Sophie.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-Sophie.IQ3_M.gguf b/Llama3-Sophie.IQ3_M.gguf new file mode 100644 index 0000000..c4004c9 --- /dev/null +++ b/Llama3-Sophie.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b24d7260a4676129e016d325003f13c7826e53eafbaa8a00cf32400d41d4f42 +size 3784823552 diff --git a/Llama3-Sophie.IQ3_S.gguf b/Llama3-Sophie.IQ3_S.gguf new file mode 100644 index 0000000..147036b --- /dev/null +++ b/Llama3-Sophie.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:422402008e1c8e6eb34d48edad116bfec58d7eb0efbddcfe5580dfa223ee9bb2 +size 3682325248 diff --git a/Llama3-Sophie.IQ3_XS.gguf b/Llama3-Sophie.IQ3_XS.gguf new file mode 100644 index 0000000..c78ffb5 --- /dev/null +++ b/Llama3-Sophie.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dea17741295b0746b9e86595170ebe34b3ecb4208943cb451262708402c4359 +size 3518747392 diff --git a/Llama3-Sophie.IQ4_XS.gguf b/Llama3-Sophie.IQ4_XS.gguf new file mode 100644 index 0000000..907108b --- /dev/null +++ b/Llama3-Sophie.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e04da60c2de3c0fd83fb61ee481d617df3ddab5db2005d59767942e4a5dd71 +size 4484363008 diff --git a/Llama3-Sophie.Q2_K.gguf b/Llama3-Sophie.Q2_K.gguf new file mode 100644 index 0000000..5c2f3ed --- /dev/null +++ b/Llama3-Sophie.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c97fc07ee8e3fdbf810a4ecda81206902e9bc957db5ea88303b81c27a0efbe4 +size 3179131648 diff --git a/Llama3-Sophie.Q3_K_L.gguf b/Llama3-Sophie.Q3_K_L.gguf new file mode 100644 index 0000000..a5c4f75 --- /dev/null +++ b/Llama3-Sophie.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82303aa1b1db4f07bf203a11ffaaf32b75c2629f32c4988cc157c567c15d6deb +size 4321956608 diff --git a/Llama3-Sophie.Q3_K_M.gguf b/Llama3-Sophie.Q3_K_M.gguf new file mode 100644 index 0000000..a31007b --- /dev/null +++ b/Llama3-Sophie.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e8ac353e116c5a5bddee6954fda4f91bd58b1d0f6555af625dd632feed46bd +size 4018918144 diff --git a/Llama3-Sophie.Q3_K_S.gguf b/Llama3-Sophie.Q3_K_S.gguf new file mode 100644 index 0000000..4e25881 --- /dev/null +++ b/Llama3-Sophie.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b861e9db25956af2d18c8d5683f3365eeb08ca74b2bbae0a2ec52a3a710a0b2 +size 3664499456 diff --git a/Llama3-Sophie.Q4_K_M.gguf b/Llama3-Sophie.Q4_K_M.gguf new file mode 100644 index 0000000..fdbdbfa --- /dev/null +++ b/Llama3-Sophie.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ba23f154059f9fedd050583b0fb0bb569402a297f19a3db8414f9401a27fb2 +size 4920734464 diff --git a/Llama3-Sophie.Q4_K_S.gguf b/Llama3-Sophie.Q4_K_S.gguf new file mode 100644 index 0000000..6299682 --- /dev/null +++ b/Llama3-Sophie.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27e6c740a4ddfccdd16a5d042865ebd54c4f3befcf9c42cc9914afb8ad57956 +size 4692669184 diff --git a/Llama3-Sophie.Q5_K_M.gguf b/Llama3-Sophie.Q5_K_M.gguf new file mode 100644 index 0000000..d9529b2 --- /dev/null +++ b/Llama3-Sophie.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5d6082525558a1f1b5370ff6fd60168a1d6073a0be793442d3e8f9da22ed794 +size 5732987648 diff --git a/Llama3-Sophie.Q5_K_S.gguf b/Llama3-Sophie.Q5_K_S.gguf new file mode 100644 index 0000000..c4a9f3c --- /dev/null +++ b/Llama3-Sophie.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e21b97fc0bec5f0e5eb747c310699cb6046b7a545628d2c4e2b24a48b4d0b2dd +size 5599294208 diff --git a/Llama3-Sophie.Q6_K.gguf b/Llama3-Sophie.Q6_K.gguf new file mode 100644 index 0000000..042a373 --- /dev/null +++ b/Llama3-Sophie.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e00fdac0bd2f8453ee47921cdd8240f95984b1028324929a6d3adbeba7b3f586 +size 6596006656 diff --git a/Llama3-Sophie.Q8_0.gguf b/Llama3-Sophie.Q8_0.gguf new file mode 100644 index 0000000..61c9f5e --- /dev/null +++ b/Llama3-Sophie.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31ebbf701db70a7b42888a017aed734f1afa3d4971a0ee831fdc24d2be7393c7 +size 8540771072 diff --git a/Llama3-Sophie.f16.gguf b/Llama3-Sophie.f16.gguf new file mode 100644 index 0000000..674cf5b --- /dev/null +++ b/Llama3-Sophie.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf7339d5c7461bf7de64e651a6248655d5c1e848928af7c87c45ac713074bb06 +size 16068891392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d3ffb93 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Aculi/Llama3-Sophie +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Aculi/Llama3-Sophie + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3-Sophie-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-Sophie-GGUF/resolve/main/Llama3-Sophie.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Sophie-GGUF/resolve/main/Llama3-Sophie.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. + +