commit 4644d2961a8b3800aec89ba7c412ada72a7db15b Author: ModelHub XC Date: Thu Oct 1 02:15:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-NIELIT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e3c440a --- /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-3.1-8B-NIELIT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-NIELIT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-NIELIT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-NIELIT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-NIELIT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-NIELIT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-NIELIT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-NIELIT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-NIELIT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-NIELIT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-NIELIT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-NIELIT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-NIELIT.IQ4_XS.gguf b/Llama-3.1-8B-NIELIT.IQ4_XS.gguf new file mode 100644 index 0000000..07d4bdb --- /dev/null +++ b/Llama-3.1-8B-NIELIT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:136a2c5e1ca0450946cf981743f08f89a2cc91719604be0fa77b107b87994e0d +size 4484363392 diff --git a/Llama-3.1-8B-NIELIT.Q2_K.gguf b/Llama-3.1-8B-NIELIT.Q2_K.gguf new file mode 100644 index 0000000..04f6880 --- /dev/null +++ b/Llama-3.1-8B-NIELIT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b0e670f3201b6d13bb5a08913cd3fd6c409cff927fd6d1c70878599e10c4ab6 +size 3179132032 diff --git a/Llama-3.1-8B-NIELIT.Q3_K_L.gguf b/Llama-3.1-8B-NIELIT.Q3_K_L.gguf new file mode 100644 index 0000000..cec0ce7 --- /dev/null +++ b/Llama-3.1-8B-NIELIT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58d335707fe3fd6d9477252d30e5318e82ee590c0cab47d0e72c64737a9e4a4d +size 4321956992 diff --git a/Llama-3.1-8B-NIELIT.Q3_K_M.gguf b/Llama-3.1-8B-NIELIT.Q3_K_M.gguf new file mode 100644 index 0000000..364f11b --- /dev/null +++ b/Llama-3.1-8B-NIELIT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:830017782df6578d7d41d5eba22f5340797a98ff8c758dcc9d6b0385c0aae160 +size 4018918528 diff --git a/Llama-3.1-8B-NIELIT.Q3_K_S.gguf b/Llama-3.1-8B-NIELIT.Q3_K_S.gguf new file mode 100644 index 0000000..05b390b --- /dev/null +++ b/Llama-3.1-8B-NIELIT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a109b5782db3693ece17190830522f4dd8eb03fbe874687a745d5cda7d7f0fbc +size 3664499840 diff --git a/Llama-3.1-8B-NIELIT.Q4_K_M.gguf b/Llama-3.1-8B-NIELIT.Q4_K_M.gguf new file mode 100644 index 0000000..e2122f0 --- /dev/null +++ b/Llama-3.1-8B-NIELIT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf7d4921d625be2cff3173faadf59dfbdc2ead073b3967cede65e41298dfa8c0 +size 4920734848 diff --git a/Llama-3.1-8B-NIELIT.Q4_K_S.gguf b/Llama-3.1-8B-NIELIT.Q4_K_S.gguf new file mode 100644 index 0000000..319b8c0 --- /dev/null +++ b/Llama-3.1-8B-NIELIT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df8f2ed757c81f5395c79b58229de72edbb6696a6440f3bb8c93dee689de8b7 +size 4692669568 diff --git a/Llama-3.1-8B-NIELIT.Q5_K_M.gguf b/Llama-3.1-8B-NIELIT.Q5_K_M.gguf new file mode 100644 index 0000000..daa745e --- /dev/null +++ b/Llama-3.1-8B-NIELIT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:202d0a6167c1110c2b2d43f1649a9b6e152bdfb19f7c00eeca84c1e75008dcbf +size 5732988032 diff --git a/Llama-3.1-8B-NIELIT.Q5_K_S.gguf b/Llama-3.1-8B-NIELIT.Q5_K_S.gguf new file mode 100644 index 0000000..23235a2 --- /dev/null +++ b/Llama-3.1-8B-NIELIT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f89e47b2c199ded966695506c40e2da9d85e8271559c1909964e2d668102dc6c +size 5599294592 diff --git a/Llama-3.1-8B-NIELIT.Q6_K.gguf b/Llama-3.1-8B-NIELIT.Q6_K.gguf new file mode 100644 index 0000000..4355a1c --- /dev/null +++ b/Llama-3.1-8B-NIELIT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca3d9e1e90b27e22ee1591a0ad3a7927bc3eb1352ddce532dae9ac68a8131fa +size 6596007040 diff --git a/Llama-3.1-8B-NIELIT.Q8_0.gguf b/Llama-3.1-8B-NIELIT.Q8_0.gguf new file mode 100644 index 0000000..429ad66 --- /dev/null +++ b/Llama-3.1-8B-NIELIT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d16032533ab14abf0dd27c93b1575790ca0a7d594fcaf6926b481147a762cc +size 8540771456 diff --git a/Llama-3.1-8B-NIELIT.f16.gguf b/Llama-3.1-8B-NIELIT.f16.gguf new file mode 100644 index 0000000..991d09e --- /dev/null +++ b/Llama-3.1-8B-NIELIT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:499b65214724d1501d7f2db18fa5a871eddd87a1352a33adb6ef7a3a97199777 +size 16068891776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3814bb7 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: yatin-ys/Llama-3.1-8B-NIELIT +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/yatin-ys/Llama-3.1-8B-NIELIT + + +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-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-NIELIT-GGUF/resolve/main/Llama-3.1-8B-NIELIT.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. + +