commit 36d70801c50ef942c5ebdf4f00e113b768d2ce46 Author: ModelHub XC Date: Sat Sep 26 05:37:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Power-Llama-3-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e0ff9d4 --- /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 +Power-Llama-3-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Power-Llama-3-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Power-Llama-3-7B-Instruct.IQ3_M.gguf b/Power-Llama-3-7B-Instruct.IQ3_M.gguf new file mode 100644 index 0000000..d394522 --- /dev/null +++ b/Power-Llama-3-7B-Instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aae3520b6d3a7ef9e934490d956523bcb920408e698045ac6fed038791469d5 +size 3014032288 diff --git a/Power-Llama-3-7B-Instruct.IQ3_S.gguf b/Power-Llama-3-7B-Instruct.IQ3_S.gguf new file mode 100644 index 0000000..f3847e1 --- /dev/null +++ b/Power-Llama-3-7B-Instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:077962c23dbf15c484319151200daf05492f4e59f71c069af40169e6a94e8d82 +size 2850257824 diff --git a/Power-Llama-3-7B-Instruct.IQ3_XS.gguf b/Power-Llama-3-7B-Instruct.IQ3_XS.gguf new file mode 100644 index 0000000..9a555e0 --- /dev/null +++ b/Power-Llama-3-7B-Instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51176e414a8a7c1ad852507359517d512c73b756ccf513e6e2066dcd0de711bb +size 2701622176 diff --git a/Power-Llama-3-7B-Instruct.IQ4_XS.gguf b/Power-Llama-3-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..d205d5f --- /dev/null +++ b/Power-Llama-3-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef01e041627bdd9cf63bb7f2ca44d2178f458d94ebcdeadcff464d18ddc52d2e +size 3531874720 diff --git a/Power-Llama-3-7B-Instruct.Q2_K.gguf b/Power-Llama-3-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..5e09806 --- /dev/null +++ b/Power-Llama-3-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fef64c4296422f929095b59c4ec96c274b20ced948439989fad46e055fa1eb9 +size 2446644640 diff --git a/Power-Llama-3-7B-Instruct.Q3_K_L.gguf b/Power-Llama-3-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..6cd29bc --- /dev/null +++ b/Power-Llama-3-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d4a7521046297d858d1ce1230d3c9644a38b36161e57f5adf5fb04e1598147c +size 3486088096 diff --git a/Power-Llama-3-7B-Instruct.Q3_K_M.gguf b/Power-Llama-3-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b9b5ddb --- /dev/null +++ b/Power-Llama-3-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aeede7198b6b7b92474378e0400b67097820929b7fce5f3edcd337de137a7a4 +size 3189603232 diff --git a/Power-Llama-3-7B-Instruct.Q3_K_S.gguf b/Power-Llama-3-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..f086df7 --- /dev/null +++ b/Power-Llama-3-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06e9abe28c1c82b9e34fbeaf47a5d9106588b1885d66088f167c796daefc7d62 +size 2850257824 diff --git a/Power-Llama-3-7B-Instruct.Q4_K_M.gguf b/Power-Llama-3-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..809092f --- /dev/null +++ b/Power-Llama-3-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:145a2aef0d58fd739bef4d0fbec7dc5d2067d21b556c532c390281510eb45042 +size 3955399072 diff --git a/Power-Llama-3-7B-Instruct.Q4_K_S.gguf b/Power-Llama-3-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..c413343 --- /dev/null +++ b/Power-Llama-3-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968b7103c5bc984c9d8470a5e40964d87409c1b02ffb3d5d8ea8e422d60bdda7 +size 3732347296 diff --git a/Power-Llama-3-7B-Instruct.Q5_K_M.gguf b/Power-Llama-3-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..8a7a04b --- /dev/null +++ b/Power-Llama-3-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d93234046d5d49896d126e839c1e4877cb905f8305fb9df65d6b33de6bcec6 +size 4639324576 diff --git a/Power-Llama-3-7B-Instruct.Q5_K_S.gguf b/Power-Llama-3-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..33a7fb4 --- /dev/null +++ b/Power-Llama-3-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3e6c54f3fcd14383b1848c10355e942e54b1abc5ca7dcb25bb603f18e25cbf +size 4510644640 diff --git a/Power-Llama-3-7B-Instruct.Q6_K.gguf b/Power-Llama-3-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..12d4173 --- /dev/null +++ b/Power-Llama-3-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:348f8836ee77472398daedaf59d9fb99971aa3cb72fe7e04dc87e43fb89efc82 +size 5365995424 diff --git a/Power-Llama-3-7B-Instruct.Q8_0.gguf b/Power-Llama-3-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..9c3babc --- /dev/null +++ b/Power-Llama-3-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0668e1f13aabd61a5629952b9a70be2ff2c98a87e5b9124efc886bbd3226aafd +size 6949608352 diff --git a/Power-Llama-3-7B-Instruct.f16.gguf b/Power-Llama-3-7B-Instruct.f16.gguf new file mode 100644 index 0000000..2534b6b --- /dev/null +++ b/Power-Llama-3-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0895fc0ffafff80577c8fe3cf2456c0df968f018758b768cb5cf42fa78351dd2 +size 13079722912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7795362 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: refine-ai/Power-Llama-3-7B-Instruct +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- KingNish +- Power Series +- llama +- llama-3 +- merge +- mergekit +- lazymergekit +--- +## About + + + + + +static quants of https://huggingface.co/refine-ai/Power-Llama-3-7B-Instruct + + +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/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.Q2_K.gguf) | Q2_K | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.IQ3_XS.gguf) | IQ3_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.IQ3_M.gguf) | IQ3_M | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.Q6_K.gguf) | Q6_K | 5.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.Q8_0.gguf) | Q8_0 | 7.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Power-Llama-3-7B-Instruct-GGUF/resolve/main/Power-Llama-3-7B-Instruct.f16.gguf) | f16 | 13.2 | 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. + +