commit 5d917adba1ef92a3680f103b213a739a66b3c325 Author: ModelHub XC Date: Tue Apr 28 05:15:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b6e8d98 --- /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-Non-filter-Lafeak64-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Non-filter-Lafeak64-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Non-filter-Lafeak64-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Non-filter-Lafeak64-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Non-filter-Lafeak64-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Non-filter-Lafeak64-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Non-filter-Lafeak64-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Non-filter-Lafeak64-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Non-filter-Lafeak64-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.IQ4_XS.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.IQ4_XS.gguf new file mode 100644 index 0000000..e25d84d --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01fdcd4dce0d3f707fa79421d499acebab9c92fae29d34ec2d96ad7231c1b300 +size 4484368384 diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.Q2_K.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.Q2_K.gguf new file mode 100644 index 0000000..1321212 --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe2948f502637a6233316c4c78f31f03718c091817dc681ba81503ac2a43cc3 +size 3179137024 diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_L.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_L.gguf new file mode 100644 index 0000000..89a0fa6 --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07f1270488880f29c12dc3fd6c33a02b19ee78fc7c4f4f0062f09a46bc2ed4ee +size 4321961984 diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_M.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_M.gguf new file mode 100644 index 0000000..7e82c3b --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:493501a5830b528256660ec09dee2b994ccef893a612c2ed4a2dd569bfb82b73 +size 4018923520 diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_S.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_S.gguf new file mode 100644 index 0000000..dd65dc2 --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e0f133723df94e827497307f49d58dad7d3326d93128b1f648e8ecee4a4ecaf +size 3664504832 diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.Q4_K_M.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.Q4_K_M.gguf new file mode 100644 index 0000000..c255631 --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afae411382b775ba4447abee566542eeabf984037e4e1acb72d366e77e3fb16d +size 4920739840 diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.Q4_K_S.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.Q4_K_S.gguf new file mode 100644 index 0000000..003ddcf --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cc4201a42cdd86d5e642137d4b1c9da9e4738b5dd0f0904b1b36611ec1c37dc +size 4692674560 diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.Q5_K_M.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.Q5_K_M.gguf new file mode 100644 index 0000000..443ef45 --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90fb8e389734005348879a5015a703b80e3e2735ad50397c1a6b662e0cff8c10 +size 5732993024 diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.Q5_K_S.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.Q5_K_S.gguf new file mode 100644 index 0000000..c636b53 --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1e18223bb5a33777a87ee0e6e02f3ccefe1079878358c72e06301e613b4cd4 +size 5599299584 diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.Q6_K.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.Q6_K.gguf new file mode 100644 index 0000000..de14bd1 --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecfce9247e838c1eb336213e0b08b042908009d71e9fdda2e46f69a3041210a6 +size 6596012032 diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.Q8_0.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.Q8_0.gguf new file mode 100644 index 0000000..eb2d4ee --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ae2a016d922373e5ae9e54dea9356d32bb6f3e83cd9fa2bb7fb6463f2402efb +size 8540776448 diff --git a/Llama-3.1-Non-filter-Lafeak64-8B.f16.gguf b/Llama-3.1-Non-filter-Lafeak64-8B.f16.gguf new file mode 100644 index 0000000..7f25687 --- /dev/null +++ b/Llama-3.1-Non-filter-Lafeak64-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69055b2de92d13ffde73ee4e78e5271be2ce24189bfbf3b89f47e5c9d4bbd694 +size 16068896768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b078002 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Yuichi1218/Llama-3.1-Non-filter-Lafeak64-8B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Yuichi1218/Llama-3.1-Non-filter-Lafeak64-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-Non-filter-Lafeak64-8B-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-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Non-filter-Lafeak64-8B-GGUF/resolve/main/Llama-3.1-Non-filter-Lafeak64-8B.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. + +