commit 87989374f785c81e3c0dbf041f59abee3a9728bd Author: ModelHub XC Date: Sat Sep 19 09:52:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/natsumura-llama3-v1.1-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9684b20 --- /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-v1.1-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +natsumura-llama3-v1.1-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8070162 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: tohur/natsumura-llama3-v1.1-8b +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/tohur/natsumura-llama3-v1.1-8b + + +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/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/natsumura-llama3-v1.1-8b-GGUF/resolve/main/natsumura-llama3-v1.1-8b.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-v1.1-8b.IQ3_M.gguf b/natsumura-llama3-v1.1-8b.IQ3_M.gguf new file mode 100644 index 0000000..b8af49a --- /dev/null +++ b/natsumura-llama3-v1.1-8b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f893f91bc0e5ee3f7f33039d0676f90e14945eff0ab0083696fa1c104d554a +size 3784823680 diff --git a/natsumura-llama3-v1.1-8b.IQ3_S.gguf b/natsumura-llama3-v1.1-8b.IQ3_S.gguf new file mode 100644 index 0000000..d18ee9a --- /dev/null +++ b/natsumura-llama3-v1.1-8b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e7fc482749919c7fcd19e1f17841a0e4826d32e9df2a977d905aec5cf1903df +size 3682325376 diff --git a/natsumura-llama3-v1.1-8b.IQ3_XS.gguf b/natsumura-llama3-v1.1-8b.IQ3_XS.gguf new file mode 100644 index 0000000..dfafd02 --- /dev/null +++ b/natsumura-llama3-v1.1-8b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74679ecbb07f5c8ef044a5a67f027f73a01bc654ab538183153f864e6b595e4e +size 3518747520 diff --git a/natsumura-llama3-v1.1-8b.IQ4_XS.gguf b/natsumura-llama3-v1.1-8b.IQ4_XS.gguf new file mode 100644 index 0000000..1bca352 --- /dev/null +++ b/natsumura-llama3-v1.1-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda7e01383085d8249ec9ea9cfcfc7ad4bb635c690686872c82506c277f002c0 +size 4484363136 diff --git a/natsumura-llama3-v1.1-8b.Q2_K.gguf b/natsumura-llama3-v1.1-8b.Q2_K.gguf new file mode 100644 index 0000000..95d7524 --- /dev/null +++ b/natsumura-llama3-v1.1-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdbe0d477a299fa6c865d32618f0aa02e78ecf68354fa6c72c36add8c97042d3 +size 3179131776 diff --git a/natsumura-llama3-v1.1-8b.Q3_K_L.gguf b/natsumura-llama3-v1.1-8b.Q3_K_L.gguf new file mode 100644 index 0000000..1c4ad7c --- /dev/null +++ b/natsumura-llama3-v1.1-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9641cd60952c77a2618bab1a02d6a6bd7e83dddb719b39ddc43a38974e45a94a +size 4321956736 diff --git a/natsumura-llama3-v1.1-8b.Q3_K_M.gguf b/natsumura-llama3-v1.1-8b.Q3_K_M.gguf new file mode 100644 index 0000000..d5d5440 --- /dev/null +++ b/natsumura-llama3-v1.1-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ca6ebd93848c175b098032fe1ac84162159f733f8c86c05962c851e18d1a153 +size 4018918272 diff --git a/natsumura-llama3-v1.1-8b.Q3_K_S.gguf b/natsumura-llama3-v1.1-8b.Q3_K_S.gguf new file mode 100644 index 0000000..f33dbf9 --- /dev/null +++ b/natsumura-llama3-v1.1-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49a145cfc9e965c7af4b832d6b60d0173fe4c84adcb81238cffa1cb021533980 +size 3664499584 diff --git a/natsumura-llama3-v1.1-8b.Q4_K_M.gguf b/natsumura-llama3-v1.1-8b.Q4_K_M.gguf new file mode 100644 index 0000000..ed4b026 --- /dev/null +++ b/natsumura-llama3-v1.1-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af2a2a575dde47427957488ca40a5833244e1889032e47ef9b032ac2aba73060 +size 4920734592 diff --git a/natsumura-llama3-v1.1-8b.Q4_K_S.gguf b/natsumura-llama3-v1.1-8b.Q4_K_S.gguf new file mode 100644 index 0000000..c6024f7 --- /dev/null +++ b/natsumura-llama3-v1.1-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96385e00b9957a689db1dcf08b94597dc33cb0f78e85f3257e71e590e41a96fa +size 4692669312 diff --git a/natsumura-llama3-v1.1-8b.Q5_K_M.gguf b/natsumura-llama3-v1.1-8b.Q5_K_M.gguf new file mode 100644 index 0000000..38cd528 --- /dev/null +++ b/natsumura-llama3-v1.1-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb11e2009f39d9db7d713e9ea951c3cdd78b81769acf120e19df487c45aec11 +size 5732987776 diff --git a/natsumura-llama3-v1.1-8b.Q5_K_S.gguf b/natsumura-llama3-v1.1-8b.Q5_K_S.gguf new file mode 100644 index 0000000..91957a3 --- /dev/null +++ b/natsumura-llama3-v1.1-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9247aeb9675be4e0f8676e8a2aaa10d6662a28dd42703729fcbffe692e5389cb +size 5599294336 diff --git a/natsumura-llama3-v1.1-8b.Q6_K.gguf b/natsumura-llama3-v1.1-8b.Q6_K.gguf new file mode 100644 index 0000000..626915a --- /dev/null +++ b/natsumura-llama3-v1.1-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e878825f8994d2e6cc02c953071909b59569d555d19eeb8b08b7ac22b65819 +size 6596006784 diff --git a/natsumura-llama3-v1.1-8b.Q8_0.gguf b/natsumura-llama3-v1.1-8b.Q8_0.gguf new file mode 100644 index 0000000..67ddc13 --- /dev/null +++ b/natsumura-llama3-v1.1-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4263db43f1b3d2d4c9e017b8fd6f05090d8b531ac97323b4819dade0bc2dc4b +size 8540771200 diff --git a/natsumura-llama3-v1.1-8b.f16.gguf b/natsumura-llama3-v1.1-8b.f16.gguf new file mode 100644 index 0000000..5cfa5db --- /dev/null +++ b/natsumura-llama3-v1.1-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e770e007f027c9eacfe523d2990431ed6403c163ba80e3e38861791f0e194fff +size 16068891520