commit fe543ddf5a155970650f7a2f67118e8d68ffd81b Author: ModelHub XC Date: Sun Jun 14 04:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-Fusion-5050-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..60e78c5 --- /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-Fusion-5050.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-5050.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-5050.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-5050.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-5050.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-5050.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-5050.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-5050.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-5050.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-5050.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-5050.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-5050.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Fusion-5050.IQ4_XS.gguf b/Llama-3.1-8B-Fusion-5050.IQ4_XS.gguf new file mode 100644 index 0000000..b2e9024 --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b45dc1e266f9ad806277f1d6334d625783cbcc87b81cb5d903d09ac8b4419ec +size 4484364000 diff --git a/Llama-3.1-8B-Fusion-5050.Q2_K.gguf b/Llama-3.1-8B-Fusion-5050.Q2_K.gguf new file mode 100644 index 0000000..b900e6a --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89bf96bc06cde47fdd6fe83bffb3fb105a5ca7fb9aff0e19affa0784f4dfd8c4 +size 3179132640 diff --git a/Llama-3.1-8B-Fusion-5050.Q3_K_L.gguf b/Llama-3.1-8B-Fusion-5050.Q3_K_L.gguf new file mode 100644 index 0000000..c5c5e59 --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a57884c00dd4b052d508983e835ccdfeda2c3769da0ead47afc56038e314e3f0 +size 4321957600 diff --git a/Llama-3.1-8B-Fusion-5050.Q3_K_M.gguf b/Llama-3.1-8B-Fusion-5050.Q3_K_M.gguf new file mode 100644 index 0000000..d378b8d --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1ac96f99bf72734581bb57791237aaa3bc8f6cf5f5b940d9cad0da0a3a8a039 +size 4018919136 diff --git a/Llama-3.1-8B-Fusion-5050.Q3_K_S.gguf b/Llama-3.1-8B-Fusion-5050.Q3_K_S.gguf new file mode 100644 index 0000000..8f91ba9 --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf3b4e44496e4e043d84c9929b515381251b1d58845a33101563a606410a6922 +size 3664500448 diff --git a/Llama-3.1-8B-Fusion-5050.Q4_K_M.gguf b/Llama-3.1-8B-Fusion-5050.Q4_K_M.gguf new file mode 100644 index 0000000..9c1ae7a --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e09770d5e99f33d43d0b5155db2f37c7074c134b94fe573237a078f3402e1c52 +size 4920735456 diff --git a/Llama-3.1-8B-Fusion-5050.Q4_K_S.gguf b/Llama-3.1-8B-Fusion-5050.Q4_K_S.gguf new file mode 100644 index 0000000..ea9231c --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de7a2d2eda25d29cc652c2024a3e91fdfc8a3f38923f2d76dd45881bd41d4a7e +size 4692670176 diff --git a/Llama-3.1-8B-Fusion-5050.Q5_K_M.gguf b/Llama-3.1-8B-Fusion-5050.Q5_K_M.gguf new file mode 100644 index 0000000..156c6fa --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b37603c412045b5a9a17c98be522dc49b6bf3d2019bd8c01dc1ee219dcd6c299 +size 5732988640 diff --git a/Llama-3.1-8B-Fusion-5050.Q5_K_S.gguf b/Llama-3.1-8B-Fusion-5050.Q5_K_S.gguf new file mode 100644 index 0000000..c6ba158 --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f0637bb2a2e63d3e2214aa710f88f8e8c805de5e949935fbbe72a487e2a278e +size 5599295200 diff --git a/Llama-3.1-8B-Fusion-5050.Q6_K.gguf b/Llama-3.1-8B-Fusion-5050.Q6_K.gguf new file mode 100644 index 0000000..965382c --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4cd14953c2c08dfad4b3b2fee6138b5430b6f36b427177dc3e4070d2213290 +size 6596007648 diff --git a/Llama-3.1-8B-Fusion-5050.Q8_0.gguf b/Llama-3.1-8B-Fusion-5050.Q8_0.gguf new file mode 100644 index 0000000..18ffaf7 --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:359761b23eeef7969f25c09987a8ffaa31109ec9e58198a9b244206c15b35a6c +size 8540772064 diff --git a/Llama-3.1-8B-Fusion-5050.f16.gguf b/Llama-3.1-8B-Fusion-5050.f16.gguf new file mode 100644 index 0000000..62711b3 --- /dev/null +++ b/Llama-3.1-8B-Fusion-5050.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b5ab74031f1598d46c483bd61b4c4b22a4f8b7193e2bc8fae57f53c37734cfb +size 16068892384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3ebee16 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: huihui-ai/Llama-3.1-8B-Fusion-5050 +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Text Generation +- llama3.1 +- text-generation-inference +- Inference Endpoints +- Transformers +- Fusion +--- +## About + + + + + + +static quants of https://huggingface.co/huihui-ai/Llama-3.1-8B-Fusion-5050 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-Fusion-5050-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-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-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-5050-GGUF/resolve/main/Llama-3.1-8B-Fusion-5050.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. + +