commit 1d3bb296e5803ec6096f00a08a8a6ea92ae94531 Author: ModelHub XC Date: Tue Sep 29 21:37:25 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9bfcd56 --- /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-Lumimaid-8B-v0.1-OAS-262k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lumimaid-8B-v0.1-OAS-262k.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lumimaid-8B-v0.1-OAS-262k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.IQ4_XS.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.IQ4_XS.gguf new file mode 100644 index 0000000..b584587 --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a219c4ad96165d48982f4c583941a719612d4cef260621f05b90104da44052f +size 4484363264 diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q2_K.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q2_K.gguf new file mode 100644 index 0000000..b99dbd2 --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47acc5ba8f387fe4a38314779ec711d097a3db451bbb6e44fa30344da620c783 +size 3179131904 diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_L.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_L.gguf new file mode 100644 index 0000000..84e3e9f --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fca39085fa77b0df1cf5af33702f71a5b34a2d05743cd0933cdf787d2068656 +size 4321956864 diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_M.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_M.gguf new file mode 100644 index 0000000..9ee107a --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c439f11bc4839a8299dee26387188944dfa06a2ff3b3e6b3aeb5f9e81bdb247c +size 4018918400 diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_S.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_S.gguf new file mode 100644 index 0000000..c7b162c --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88889c938a364e08da8e848e55738bbcd8506da4b4e9da051248849c8ce00209 +size 3664499712 diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q4_K_M.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q4_K_M.gguf new file mode 100644 index 0000000..48590b0 --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2069522ea52dd74c9972d2ef4afe767592a55387cfefcf250880ccb8c252abd4 +size 4920734720 diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q4_K_S.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q4_K_S.gguf new file mode 100644 index 0000000..88eedd3 --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:032603eb25b66c00b4b378e23bf0fffc2f7db9dc7bb424ffec35f7780a8a42fc +size 4692669440 diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q5_K_M.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q5_K_M.gguf new file mode 100644 index 0000000..6f6f0f9 --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f410178a0a5eb2ae8f7d8ab24b2f4bb6e1210f0f1ce09fa529d172743493e0b9 +size 5732987904 diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q5_K_S.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q5_K_S.gguf new file mode 100644 index 0000000..f96b442 --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:991b61b001b23ea492debe9c8aeafc1026f67f08a51bef311a471199d29f0a31 +size 5599294464 diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q6_K.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q6_K.gguf new file mode 100644 index 0000000..c0f90ba --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4f1239e2a0fcd5aaac2f8749f862a4dfc4229a45116ea35b3703244803c61e0 +size 6596006912 diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q8_0.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q8_0.gguf new file mode 100644 index 0000000..361c7c7 --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d1a024ee1dafe9ba40a1d790195a94f0e55c9c32545ca5203e95bd04936c916 +size 8540771328 diff --git a/Llama-3-Lumimaid-8B-v0.1-OAS-262k.f16.gguf b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.f16.gguf new file mode 100644 index 0000000..053184a --- /dev/null +++ b/Llama-3-Lumimaid-8B-v0.1-OAS-262k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0daa41f5f97aa8d9defc28dd6bdaaf00cfc19bef163b0632bcfec5a235712df7 +size 16068891648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ee08db7 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: NeverSleepHistorical/Llama-3-Lumimaid-8B-v0.1-OAS-262k +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/NeverSleepHistorical/Llama-3-Lumimaid-8B-v0.1-OAS-262k + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-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/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lumimaid-8B-v0.1-OAS-262k-GGUF/resolve/main/Llama-3-Lumimaid-8B-v0.1-OAS-262k.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. + +