commit 296511c12b5e5bf1a70c273c71037abc6656b3d8 Author: ModelHub XC Date: Sun May 31 09:55:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ba94799 --- /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 +Llama-3-8B_Suzume_DARE_TIES0.5_v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_DARE_TIES0.5_v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.IQ4_XS.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.IQ4_XS.gguf new file mode 100644 index 0000000..43a125d --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a1cc851a76a15beaa5f38f01f86a39ec2ca4eeafdd6dd625183f210dfff6cbf +size 4484363936 diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q2_K.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q2_K.gguf new file mode 100644 index 0000000..4e047c7 --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73289b9a8b69476a6706abb66609cdf0795b67915faa06b50e0804e12544bdb +size 3179132576 diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_L.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_L.gguf new file mode 100644 index 0000000..e400daa --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc86ee0877e7a65da56e81a5fcec3b1426c48bf283709321085a61f399ed807 +size 4321957536 diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_M.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_M.gguf new file mode 100644 index 0000000..5b67293 --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e334881d2373384c36803d00aae935b3250b75883ca63c5d321174321b48d851 +size 4018919072 diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_S.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_S.gguf new file mode 100644 index 0000000..6d953f4 --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37c2457bd2ef15c892f80eee3f7aacbf0c7d037f60e6f4df220f716b2891114c +size 3664500384 diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q4_K_M.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q4_K_M.gguf new file mode 100644 index 0000000..3f90b7e --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d499d23e988c9aa3f0adafdbcafdfb636bd87bca6dc576c14a54de43de35d96 +size 4920735392 diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q4_K_S.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q4_K_S.gguf new file mode 100644 index 0000000..2f54836 --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc3a923df7c8e6eb97075eb3dac67dbc40e9b4a2ff6e8542fd74ed7fcca2b9e +size 4692670112 diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q5_K_M.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q5_K_M.gguf new file mode 100644 index 0000000..2792640 --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9ae8eb6b3092b7fbb8ca5a53df2cc0078ffe1804e94e3fd300cf0454418f349 +size 5732988576 diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q5_K_S.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q5_K_S.gguf new file mode 100644 index 0000000..5ee0ea6 --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf1607dc8f4f6d256e3c9a755bb47f5455bd5388bc74fba6b02116b78937048 +size 5599295136 diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q6_K.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q6_K.gguf new file mode 100644 index 0000000..88985f0 --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a5bbfc33d5363953bcf1233e5eff63e572c75a0e216432cd61c2930ac388a4 +size 6596007584 diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q8_0.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q8_0.gguf new file mode 100644 index 0000000..d49da41 --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a671ce8c1ccbda33e93bd9f310f9e2328a485d31362846fbd84ceea18cb2a1c +size 8540772000 diff --git a/Llama-3-8B_Suzume_DARE_TIES0.5_v2.f16.gguf b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.f16.gguf new file mode 100644 index 0000000..652ce08 --- /dev/null +++ b/Llama-3-8B_Suzume_DARE_TIES0.5_v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7d02771a7250a9f0db31f3ccf27d8233dce27b4bc6bd5ac3618b0bc4af5103d +size 16068892320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f101557 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: noirchan/Llama-3-8B_Suzume_DARE_TIES0.5_v2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/noirchan/Llama-3-8B_Suzume_DARE_TIES0.5_v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-8B_Suzume_DARE_TIES0.5_v2-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/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF/resolve/main/Llama-3-8B_Suzume_DARE_TIES0.5_v2.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. + +