commit 2afb0a5277e020e34a147e586a781ef59be05076 Author: ModelHub XC Date: Sat Sep 19 09:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/natsumura-llama3.1-v1.0-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..02d4e85 --- /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 +natsumura-llama3.1-v1.0-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3.1-v1.0-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7c3691e --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: tohur/natsumura-llama3.1-v1.0-8b +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/tohur/natsumura-llama3.1-v1.0-8b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-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/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3.1-v1.0-8b-GGUF/resolve/main/natsumura-llama3.1-v1.0-8b.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. + + diff --git a/natsumura-llama3.1-v1.0-8b.IQ3_M.gguf b/natsumura-llama3.1-v1.0-8b.IQ3_M.gguf new file mode 100644 index 0000000..78ccab2 --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f10425e2bccf8f0dbf6b55b03713437e24040d13432540dfd5033aac85953929 +size 3784824928 diff --git a/natsumura-llama3.1-v1.0-8b.IQ3_S.gguf b/natsumura-llama3.1-v1.0-8b.IQ3_S.gguf new file mode 100644 index 0000000..1d6ecca --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be744240405e18f4bbb47bcf14f0c8ebfdd2b7f60fd2c141d47213e98c7d8a1b +size 3682326624 diff --git a/natsumura-llama3.1-v1.0-8b.IQ3_XS.gguf b/natsumura-llama3.1-v1.0-8b.IQ3_XS.gguf new file mode 100644 index 0000000..08483cb --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd6ec5cb4b14e7c0f0ada483b080271a8880ca0bba81d49189b22a3ab0f71c7 +size 3518748768 diff --git a/natsumura-llama3.1-v1.0-8b.IQ4_XS.gguf b/natsumura-llama3.1-v1.0-8b.IQ4_XS.gguf new file mode 100644 index 0000000..5d5225e --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e1abbe063ace3eaf48bac249431a95ed95ced2606194195c47c5eea88ae26e7 +size 4484364384 diff --git a/natsumura-llama3.1-v1.0-8b.Q2_K.gguf b/natsumura-llama3.1-v1.0-8b.Q2_K.gguf new file mode 100644 index 0000000..0b259d2 --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f2a582764ed6c505cadc02fa4cf756666f061cedf6dab7fcdd6e1420a90046 +size 3179133024 diff --git a/natsumura-llama3.1-v1.0-8b.Q3_K_L.gguf b/natsumura-llama3.1-v1.0-8b.Q3_K_L.gguf new file mode 100644 index 0000000..46e4372 --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa83555b69b1b01e9a43a6508df7efbbaeea5cf59e12d2d1e7a8a8d01e1722b +size 4321957984 diff --git a/natsumura-llama3.1-v1.0-8b.Q3_K_M.gguf b/natsumura-llama3.1-v1.0-8b.Q3_K_M.gguf new file mode 100644 index 0000000..6442f74 --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a5d078df2fa4219e37733c389db7d4370b7bf98f692ab55f8847fb7dd2a3cd2 +size 4018919520 diff --git a/natsumura-llama3.1-v1.0-8b.Q3_K_S.gguf b/natsumura-llama3.1-v1.0-8b.Q3_K_S.gguf new file mode 100644 index 0000000..82ff188 --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07c1d5c8081ffb612486a505d80f24dc6807e11303ad5d8fe3b8758d3c84d654 +size 3664500832 diff --git a/natsumura-llama3.1-v1.0-8b.Q4_K_M.gguf b/natsumura-llama3.1-v1.0-8b.Q4_K_M.gguf new file mode 100644 index 0000000..7db425f --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d7b2a9acabe8ae5b60bbee4a50b0f6d4b5e29356df33165fbc0a7664f44c7f +size 4920735840 diff --git a/natsumura-llama3.1-v1.0-8b.Q4_K_S.gguf b/natsumura-llama3.1-v1.0-8b.Q4_K_S.gguf new file mode 100644 index 0000000..d175fc2 --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061c39b3910ace5b5b66e97e000f40441a5cd968ca7cf9f46a782411883882fb +size 4692670560 diff --git a/natsumura-llama3.1-v1.0-8b.Q5_K_M.gguf b/natsumura-llama3.1-v1.0-8b.Q5_K_M.gguf new file mode 100644 index 0000000..f4dceb2 --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff031d6b505c75befdea7df2e09585063f5d5c374bdd9f7ec15d02fbd663333d +size 5732989024 diff --git a/natsumura-llama3.1-v1.0-8b.Q5_K_S.gguf b/natsumura-llama3.1-v1.0-8b.Q5_K_S.gguf new file mode 100644 index 0000000..789f53c --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d523167fe7fce4d998300d198ad43a97d53237c18448b60e60cb6d1fe05810 +size 5599295584 diff --git a/natsumura-llama3.1-v1.0-8b.Q6_K.gguf b/natsumura-llama3.1-v1.0-8b.Q6_K.gguf new file mode 100644 index 0000000..29aaedb --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc52cf5ab181fae263cc38d6f17bc314171c80424a65f1ecec496b121bbda3af +size 6596008032 diff --git a/natsumura-llama3.1-v1.0-8b.Q8_0.gguf b/natsumura-llama3.1-v1.0-8b.Q8_0.gguf new file mode 100644 index 0000000..0500a6f --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fa6ba404bbefa1204329e539c7dcd9f3abc1bb287b67bfcbca698ef2ab7810f +size 8540772448 diff --git a/natsumura-llama3.1-v1.0-8b.f16.gguf b/natsumura-llama3.1-v1.0-8b.f16.gguf new file mode 100644 index 0000000..3488c9d --- /dev/null +++ b/natsumura-llama3.1-v1.0-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780c2c7892fc0bd8f7c28c44ea10e285f6b9c6a79afc5c43b467d2ec99207926 +size 16068892768