commit ade6d6fda5923acaeff14407efed2768657803cb Author: ModelHub XC Date: Sat Aug 1 00:09:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-1-8B-Italian-FVT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ac30f45 --- /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-Italian-FVT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-1-8B-Italian-FVT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-1-8B-Italian-FVT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-1-8B-Italian-FVT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-1-8B-Italian-FVT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-1-8B-Italian-FVT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-1-8B-Italian-FVT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-1-8B-Italian-FVT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-1-8B-Italian-FVT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-1-8B-Italian-FVT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-1-8B-Italian-FVT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-1-8B-Italian-FVT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-1-8B-Italian-FVT.IQ4_XS.gguf b/Llama-3-1-8B-Italian-FVT.IQ4_XS.gguf new file mode 100644 index 0000000..82d7ef8 --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7635671d44e1f1d4ec95b1039ae35eed51274737ee55dfb07c0f0ab03edc704 +size 3948710976 diff --git a/Llama-3-1-8B-Italian-FVT.Q2_K.gguf b/Llama-3-1-8B-Italian-FVT.Q2_K.gguf new file mode 100644 index 0000000..48b2711 --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f538124b718377b943765b3a91ff6b05a3e980591092579a1085b5868be089f +size 2722925632 diff --git a/Llama-3-1-8B-Italian-FVT.Q3_K_L.gguf b/Llama-3-1-8B-Italian-FVT.Q3_K_L.gguf new file mode 100644 index 0000000..69b840e --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b78447a76c16300dd760df2da3b7b3021b3098cd1917aff53a6669b8dccab773 +size 3826027584 diff --git a/Llama-3-1-8B-Italian-FVT.Q3_K_M.gguf b/Llama-3-1-8B-Italian-FVT.Q3_K_M.gguf new file mode 100644 index 0000000..623856a --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a48bf2c77af49b0902d26e2185b0eff6465a273369c6e9d956f8d5e98e23925 +size 3522989120 diff --git a/Llama-3-1-8B-Italian-FVT.Q3_K_S.gguf b/Llama-3-1-8B-Italian-FVT.Q3_K_S.gguf new file mode 100644 index 0000000..29254b8 --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3156f704d1d249715af5a3f26554a80f445bca8e67382fd6332269be8036c5d +size 3168570432 diff --git a/Llama-3-1-8B-Italian-FVT.Q4_K_M.gguf b/Llama-3-1-8B-Italian-FVT.Q4_K_M.gguf new file mode 100644 index 0000000..39e6727 --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9178ebc50a55e14300fcb9043a5b7331a14cd3c05653c902924c59700e2bd49b +size 4372859968 diff --git a/Llama-3-1-8B-Italian-FVT.Q4_K_S.gguf b/Llama-3-1-8B-Italian-FVT.Q4_K_S.gguf new file mode 100644 index 0000000..67dacef --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7832cb5399e4abaef6b1d3832d2d701bcd20358bdbe2be7bc4532725040be23 +size 4144794688 diff --git a/Llama-3-1-8B-Italian-FVT.Q5_K_M.gguf b/Llama-3-1-8B-Italian-FVT.Q5_K_M.gguf new file mode 100644 index 0000000..a4689f0 --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45854077f458a5cccffd9d4e5a9cb7f9e434da13f1a484e8378550e5a61ed698 +size 5136223296 diff --git a/Llama-3-1-8B-Italian-FVT.Q5_K_S.gguf b/Llama-3-1-8B-Italian-FVT.Q5_K_S.gguf new file mode 100644 index 0000000..816d3ef --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce05ca2b6d186f42215afdd5a3f90f11bda2dab5b2f5a121dded2caab3cf592 +size 5002529856 diff --git a/Llama-3-1-8B-Italian-FVT.Q6_K.gguf b/Llama-3-1-8B-Italian-FVT.Q6_K.gguf new file mode 100644 index 0000000..6538faa --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72810cd3592194b93241a3e57bb856da55a4a35575fc029221991d29565b6f41 +size 5947296832 diff --git a/Llama-3-1-8B-Italian-FVT.Q8_0.gguf b/Llama-3-1-8B-Italian-FVT.Q8_0.gguf new file mode 100644 index 0000000..aee7f6a --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26133e54183f6e3010b6731cc9acf0218358c5ab802e81a239b8076360e6921e +size 7702613056 diff --git a/Llama-3-1-8B-Italian-FVT.f16.gguf b/Llama-3-1-8B-Italian-FVT.f16.gguf new file mode 100644 index 0000000..f7ad122 --- /dev/null +++ b/Llama-3-1-8B-Italian-FVT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0010b92e54cc66c7a3f497bcc6f90b704dab5ea4c771adc5f8aa94f994bbc225 +size 14497385536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2268e5f --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: SemanticAlignment/Llama-3.1-8B-Italian-FVT +language: +- it +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/SemanticAlignment/Llama-3.1-8B-Italian-FVT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-1-8B-Italian-FVT-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-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-1-8B-Italian-FVT-GGUF/resolve/main/Llama-3-1-8B-Italian-FVT.f16.gguf) | f16 | 14.6 | 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. + +