commit 85a23e8c168952d6bb5eddab26832ed3c9be264f Author: ModelHub XC Date: Thu Aug 27 09:38:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Inputoutput_SFT_Llama3_3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1ee1ae6 --- /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 +Inputoutput_SFT_Llama3_3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Inputoutput_SFT_Llama3_3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Inputoutput_SFT_Llama3_3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Inputoutput_SFT_Llama3_3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Inputoutput_SFT_Llama3_3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Inputoutput_SFT_Llama3_3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Inputoutput_SFT_Llama3_3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Inputoutput_SFT_Llama3_3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Inputoutput_SFT_Llama3_3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Inputoutput_SFT_Llama3_3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Inputoutput_SFT_Llama3_3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Inputoutput_SFT_Llama3_3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Inputoutput_SFT_Llama3_3B.IQ4_XS.gguf b/Inputoutput_SFT_Llama3_3B.IQ4_XS.gguf new file mode 100644 index 0000000..495d582 --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:351d98481a51327e0170cc7d6d40f97e2254d36e6286bce40b6b6606d3301346 +size 2050220608 diff --git a/Inputoutput_SFT_Llama3_3B.Q2_K.gguf b/Inputoutput_SFT_Llama3_3B.Q2_K.gguf new file mode 100644 index 0000000..0729fe7 --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0afa8da89ebc05d3d5cbe91aedb5159538fb146af3da33619295dadbd4b041d5 +size 1493217856 diff --git a/Inputoutput_SFT_Llama3_3B.Q3_K_L.gguf b/Inputoutput_SFT_Llama3_3B.Q3_K_L.gguf new file mode 100644 index 0000000..2fc42c7 --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b47c873bd0be8cb504ae7d1abb0a10f8fb06cc233c8fe511973912120d86379 +size 1984645696 diff --git a/Inputoutput_SFT_Llama3_3B.Q3_K_M.gguf b/Inputoutput_SFT_Llama3_3B.Q3_K_M.gguf new file mode 100644 index 0000000..8b6e377 --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bab8afb154598a78ac082bbbb3fb36c9749425e26438fa257511616e933a206 +size 1856457280 diff --git a/Inputoutput_SFT_Llama3_3B.Q3_K_S.gguf b/Inputoutput_SFT_Llama3_3B.Q3_K_S.gguf new file mode 100644 index 0000000..a066f40 --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb3409bdd76f30d8ab8cc4f0bbd050980a427738caa2a29fc5ceaa37f94f7f2d +size 1712147008 diff --git a/Inputoutput_SFT_Llama3_3B.Q4_K_M.gguf b/Inputoutput_SFT_Llama3_3B.Q4_K_M.gguf new file mode 100644 index 0000000..82fcd46 --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0db383e4ed99b005378c95c5e17349f4aa55e30f9531f8b97a6926b6eedc2652 +size 2241004096 diff --git a/Inputoutput_SFT_Llama3_3B.Q4_K_S.gguf b/Inputoutput_SFT_Llama3_3B.Q4_K_S.gguf new file mode 100644 index 0000000..558973b --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6199d6bbfdb862afb08279df78da6de0c8d2bd51c426c21ddda299229c5ca460 +size 2149827136 diff --git a/Inputoutput_SFT_Llama3_3B.Q5_K_M.gguf b/Inputoutput_SFT_Llama3_3B.Q5_K_M.gguf new file mode 100644 index 0000000..bea95b9 --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a0cf89cc55d4a83cf84416ddf40a5ddab6170780d89e0b8f4174ee35e774ad +size 2593030720 diff --git a/Inputoutput_SFT_Llama3_3B.Q5_K_S.gguf b/Inputoutput_SFT_Llama3_3B.Q5_K_S.gguf new file mode 100644 index 0000000..d679fc4 --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2cb6151bf35b70ebc54102a7c91f3426bfd25ea425c78a039aec42ef0bca700 +size 2540388928 diff --git a/Inputoutput_SFT_Llama3_3B.Q6_K.gguf b/Inputoutput_SFT_Llama3_3B.Q6_K.gguf new file mode 100644 index 0000000..463d3e4 --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ad497e782dd6822a99787bbc48abfef6429a37ab86286bc8ead78a8d520a0d +size 2967059008 diff --git a/Inputoutput_SFT_Llama3_3B.Q8_0.gguf b/Inputoutput_SFT_Llama3_3B.Q8_0.gguf new file mode 100644 index 0000000..fad2672 --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aed78784fb26c02e431ed691da696bdbe29bbec60161fd1252b703232581b920 +size 3840526912 diff --git a/Inputoutput_SFT_Llama3_3B.f16.gguf b/Inputoutput_SFT_Llama3_3B.f16.gguf new file mode 100644 index 0000000..8b03637 --- /dev/null +++ b/Inputoutput_SFT_Llama3_3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af2a5b5cf815c1d8015dbda4f2ecce370f4769637ab76fe21306fd17897d4ec +size 7221692992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d31a372 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Shiyu-Lab/Inputoutput_SFT_Llama3_3B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Shiyu-Lab/Inputoutput_SFT_Llama3_3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Inputoutput_SFT_Llama3_3B-GGUF).*** + +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/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Inputoutput_SFT_Llama3_3B-GGUF/resolve/main/Inputoutput_SFT_Llama3_3B.f16.gguf) | f16 | 7.3 | 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. + +