commit bb109587d806d744aebae020cba696fafe4da512 Author: ModelHub XC Date: Fri Aug 21 09:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLIMONIIE_llama3-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..49fd4c7 --- /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 +LLIMONIIE_llama3-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLIMONIIE_llama3-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLIMONIIE_llama3-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLIMONIIE_llama3-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLIMONIIE_llama3-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLIMONIIE_llama3-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLIMONIIE_llama3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLIMONIIE_llama3-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLIMONIIE_llama3-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLIMONIIE_llama3-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLIMONIIE_llama3-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLIMONIIE_llama3-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLIMONIIE_llama3-8b.IQ4_XS.gguf b/LLIMONIIE_llama3-8b.IQ4_XS.gguf new file mode 100644 index 0000000..9b17ee4 --- /dev/null +++ b/LLIMONIIE_llama3-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f10fc3121d5b67147a8479fb48d1514cb1dca8449bdcd9ac2c5a491fe34f44ea +size 4484363840 diff --git a/LLIMONIIE_llama3-8b.Q2_K.gguf b/LLIMONIIE_llama3-8b.Q2_K.gguf new file mode 100644 index 0000000..55abae2 --- /dev/null +++ b/LLIMONIIE_llama3-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ad7c045f440c336b3f6d38ae46f6b21455f09d82670f76c3cb43ff6e1542b7 +size 3179132480 diff --git a/LLIMONIIE_llama3-8b.Q3_K_L.gguf b/LLIMONIIE_llama3-8b.Q3_K_L.gguf new file mode 100644 index 0000000..b1c09e3 --- /dev/null +++ b/LLIMONIIE_llama3-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c3e9f91b9b1861160bef1a49d5a54bd4830d334beab69081eb462ac7995382 +size 4321957440 diff --git a/LLIMONIIE_llama3-8b.Q3_K_M.gguf b/LLIMONIIE_llama3-8b.Q3_K_M.gguf new file mode 100644 index 0000000..bf41567 --- /dev/null +++ b/LLIMONIIE_llama3-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc6b5e6209b57af581602084fd5d648f64231a41b3b7e04da0f41c398ee89ba6 +size 4018918976 diff --git a/LLIMONIIE_llama3-8b.Q3_K_S.gguf b/LLIMONIIE_llama3-8b.Q3_K_S.gguf new file mode 100644 index 0000000..1e6238b --- /dev/null +++ b/LLIMONIIE_llama3-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1051c5f6b4654055c9979797f0cdf4c1e8eabcd37cc9e9f58f15f41190ca5b12 +size 3664500288 diff --git a/LLIMONIIE_llama3-8b.Q4_K_M.gguf b/LLIMONIIE_llama3-8b.Q4_K_M.gguf new file mode 100644 index 0000000..dba5755 --- /dev/null +++ b/LLIMONIIE_llama3-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:014dba8dde59afde973a46558bdcb929823a29cc32d7e871c34e0fdee05c92a0 +size 4920735296 diff --git a/LLIMONIIE_llama3-8b.Q4_K_S.gguf b/LLIMONIIE_llama3-8b.Q4_K_S.gguf new file mode 100644 index 0000000..39bea81 --- /dev/null +++ b/LLIMONIIE_llama3-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2508d1898a509b3fea40e5eaaa79d7e41eed70fcd0fdfa63caeb7da53a54c000 +size 4692670016 diff --git a/LLIMONIIE_llama3-8b.Q5_K_M.gguf b/LLIMONIIE_llama3-8b.Q5_K_M.gguf new file mode 100644 index 0000000..526b4b4 --- /dev/null +++ b/LLIMONIIE_llama3-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c821959382da96f79fa5c223009459d4f2791052d20985fca4ce49fcd808be +size 5732988480 diff --git a/LLIMONIIE_llama3-8b.Q5_K_S.gguf b/LLIMONIIE_llama3-8b.Q5_K_S.gguf new file mode 100644 index 0000000..f0861b4 --- /dev/null +++ b/LLIMONIIE_llama3-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c767092f0f3361e8db1264558d39f5b1dd1b9877bb37d04c229fb4ecd1cb974e +size 5599295040 diff --git a/LLIMONIIE_llama3-8b.Q6_K.gguf b/LLIMONIIE_llama3-8b.Q6_K.gguf new file mode 100644 index 0000000..e157776 --- /dev/null +++ b/LLIMONIIE_llama3-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1084ee8fbed88dc65b66942024bb18900972badebda4cccbd56c11a84ac51725 +size 6596007488 diff --git a/LLIMONIIE_llama3-8b.Q8_0.gguf b/LLIMONIIE_llama3-8b.Q8_0.gguf new file mode 100644 index 0000000..210d859 --- /dev/null +++ b/LLIMONIIE_llama3-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bbfaab0e167ac3f29de3b11389eb88e86899c29110760a761408b158c10bd69 +size 8540771904 diff --git a/LLIMONIIE_llama3-8b.f16.gguf b/LLIMONIIE_llama3-8b.f16.gguf new file mode 100644 index 0000000..c080a62 --- /dev/null +++ b/LLIMONIIE_llama3-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7129e96ccebcbbb6c7a0cad2ce5ffcf95cec762a104cb80dd7832ae361e3888 +size 16068892224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ba84b0b --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: leopiano98/LLIMONIIE_llama3-8b +language: +- en +- it +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- unsloth +- llama3 +- NER +- RE +- OIE +- LLIMONIIE +--- +## About + + + + + + +static quants of https://huggingface.co/leopiano98/LLIMONIIE_llama3-8b + + +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/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLIMONIIE_llama3-8b-GGUF/resolve/main/LLIMONIIE_llama3-8b.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. + +