commit f2952448f3c7be036123b70c2e9a7b07a40f92be Author: ModelHub XC Date: Mon Sep 28 12:38:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-suzume_liner0.5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cd70dcb --- /dev/null +++ b/.gitattributes @@ -0,0 +1,45 @@ +*.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_liner0.5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.5.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-suzume_liner0.5.IQ4_XS.gguf b/Llama-3-8B-suzume_liner0.5.IQ4_XS.gguf new file mode 100644 index 0000000..eeb6b6d --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b25e8f38ab3d04ac1ce562f8b36d918ed41c1037f3f35758abae4151188411 +size 4484363936 diff --git a/Llama-3-8B-suzume_liner0.5.Q2_K.gguf b/Llama-3-8B-suzume_liner0.5.Q2_K.gguf new file mode 100644 index 0000000..7fefcc1 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323857b547818881ab985c52b0df0b118ebd65d3bf9282bb6597c996efe7ab7f +size 3179132576 diff --git a/Llama-3-8B-suzume_liner0.5.Q3_K_L.gguf b/Llama-3-8B-suzume_liner0.5.Q3_K_L.gguf new file mode 100644 index 0000000..3e7ee57 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b03d1f0245e6995c99d4601db7dd83690d8461851e51d4959eb437702a986d35 +size 4321957536 diff --git a/Llama-3-8B-suzume_liner0.5.Q3_K_M.gguf b/Llama-3-8B-suzume_liner0.5.Q3_K_M.gguf new file mode 100644 index 0000000..7e86cda --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ca221195f4b7afd30a13c6f0ba33ef10a86ecfdfb669312d58569dcb2b2e574 +size 4018919072 diff --git a/Llama-3-8B-suzume_liner0.5.Q3_K_S.gguf b/Llama-3-8B-suzume_liner0.5.Q3_K_S.gguf new file mode 100644 index 0000000..0aa4198 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8abdae0c18f9ee80cb4bff4ae44f99ca6c52e1918a03ab6591f86a30ab217967 +size 3664500384 diff --git a/Llama-3-8B-suzume_liner0.5.Q4_K_M.gguf b/Llama-3-8B-suzume_liner0.5.Q4_K_M.gguf new file mode 100644 index 0000000..26c8261 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e3e3a8b7130e3df48452437e0ba22006833c878e1d0e9605f69a9b326aca365 +size 4920735392 diff --git a/Llama-3-8B-suzume_liner0.5.Q4_K_S.gguf b/Llama-3-8B-suzume_liner0.5.Q4_K_S.gguf new file mode 100644 index 0000000..0504172 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:722565781a469b1b61333b69ea53cafaea11b60c73f99d39969c41b12a1471f9 +size 4692670112 diff --git a/Llama-3-8B-suzume_liner0.5.Q5_K_M.gguf b/Llama-3-8B-suzume_liner0.5.Q5_K_M.gguf new file mode 100644 index 0000000..358e902 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:545ba6601cb6872770cb2cbdc4053204ca40fb1f6b125f736dc7d216bc587622 +size 5732988576 diff --git a/Llama-3-8B-suzume_liner0.5.Q5_K_S.gguf b/Llama-3-8B-suzume_liner0.5.Q5_K_S.gguf new file mode 100644 index 0000000..6c72af0 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06db9759ec757aaf3ea71644f5445b5d5700e96fc2841e72ca86edf2fbac21ea +size 5599295136 diff --git a/Llama-3-8B-suzume_liner0.5.Q6_K.gguf b/Llama-3-8B-suzume_liner0.5.Q6_K.gguf new file mode 100644 index 0000000..9a2ef4a --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d136b3d83c6f1a1fbc7200b197cfae760d828c062f2bdfe21cbfe2d90feb94c +size 6596007584 diff --git a/Llama-3-8B-suzume_liner0.5.Q8_0.gguf b/Llama-3-8B-suzume_liner0.5.Q8_0.gguf new file mode 100644 index 0000000..a4d7efb --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61fe53b12b745a9c1aa81dceee3b479d8b9b3bdf7637edea7fd053b7a78ca8ce +size 8540772000 diff --git a/Llama-3-8B-suzume_liner0.5.f16.gguf b/Llama-3-8B-suzume_liner0.5.f16.gguf new file mode 100644 index 0000000..bd986eb --- /dev/null +++ b/Llama-3-8B-suzume_liner0.5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b9f2f9a41b5f478e456957f61983b2b8ac14524c13f20566d1d2b57d42750f4 +size 16068892320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a5941ad --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: noirchan/Llama-3-8B-suzume_liner0.5 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/noirchan/Llama-3-8B-suzume_liner0.5 + + +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_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.5-GGUF/resolve/main/Llama-3-8B-suzume_liner0.5.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. + +