commit 816fdb29f526d06d2c0ff62df81035d6f780ed4a Author: ModelHub XC Date: Fri Aug 7 04:11:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8b-ITA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..03cf033 --- /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-ITA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-ITA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-ITA.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-ITA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-ITA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-ITA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-ITA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-ITA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-ITA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-ITA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-ITA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8b-ITA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8b-ITA.IQ4_XS.gguf b/Llama-3.1-8b-ITA.IQ4_XS.gguf new file mode 100644 index 0000000..fdcc699 --- /dev/null +++ b/Llama-3.1-8b-ITA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df01dbfc76715e5d8948d24a2f5f7dcd238ef9e6ae5c6ee03c03e3f8185723da +size 4484363680 diff --git a/Llama-3.1-8b-ITA.Q2_K.gguf b/Llama-3.1-8b-ITA.Q2_K.gguf new file mode 100644 index 0000000..daaf6de --- /dev/null +++ b/Llama-3.1-8b-ITA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af4f6bedfd6cfcc38950cf6d591ca5d1475efdc3b921928f1ec40ee11c2c273d +size 3179132320 diff --git a/Llama-3.1-8b-ITA.Q3_K_L.gguf b/Llama-3.1-8b-ITA.Q3_K_L.gguf new file mode 100644 index 0000000..2c7fcf4 --- /dev/null +++ b/Llama-3.1-8b-ITA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a522ccf76a357339149cd0aecb8cbd4366d5d9ab3ef87628f7480abe5d28518 +size 4321957280 diff --git a/Llama-3.1-8b-ITA.Q3_K_M.gguf b/Llama-3.1-8b-ITA.Q3_K_M.gguf new file mode 100644 index 0000000..4fe94bd --- /dev/null +++ b/Llama-3.1-8b-ITA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5f19a84cbfd9a1a3efad3a04ed4908d4e18b703128ec5e995a6fabe433115d5 +size 4018918816 diff --git a/Llama-3.1-8b-ITA.Q3_K_S.gguf b/Llama-3.1-8b-ITA.Q3_K_S.gguf new file mode 100644 index 0000000..980c670 --- /dev/null +++ b/Llama-3.1-8b-ITA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46f1c572f4e3963c4c51292925913efbfc657732517b880e2c9195cee8a0dd5d +size 3664500128 diff --git a/Llama-3.1-8b-ITA.Q4_K_M.gguf b/Llama-3.1-8b-ITA.Q4_K_M.gguf new file mode 100644 index 0000000..89195a4 --- /dev/null +++ b/Llama-3.1-8b-ITA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1b3beafb0a60abea44c9e052cd780cfaf492ff8850d957769c3a56bda813369 +size 4920735136 diff --git a/Llama-3.1-8b-ITA.Q4_K_S.gguf b/Llama-3.1-8b-ITA.Q4_K_S.gguf new file mode 100644 index 0000000..4a0038a --- /dev/null +++ b/Llama-3.1-8b-ITA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27c94fd8699dc7a6560a33c50f1eff1e47a86f8b95e9944080ae0e7e193d82a +size 4692669856 diff --git a/Llama-3.1-8b-ITA.Q5_K_M.gguf b/Llama-3.1-8b-ITA.Q5_K_M.gguf new file mode 100644 index 0000000..8a26465 --- /dev/null +++ b/Llama-3.1-8b-ITA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c58bad6ee5a6732feb1563be7bfa1cb107b4288b28a4700290e4bddbad93dd7 +size 5732988320 diff --git a/Llama-3.1-8b-ITA.Q5_K_S.gguf b/Llama-3.1-8b-ITA.Q5_K_S.gguf new file mode 100644 index 0000000..433d439 --- /dev/null +++ b/Llama-3.1-8b-ITA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79fe597d0b1a38a4128f419bc09085322f515df05923148c6f66a84c5141e07b +size 5599294880 diff --git a/Llama-3.1-8b-ITA.Q6_K.gguf b/Llama-3.1-8b-ITA.Q6_K.gguf new file mode 100644 index 0000000..9cc5106 --- /dev/null +++ b/Llama-3.1-8b-ITA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26871efdd38190ba65606238c70d33e1954d4e7fa096752f6595c1c5f47fc798 +size 6596007328 diff --git a/Llama-3.1-8b-ITA.Q8_0.gguf b/Llama-3.1-8b-ITA.Q8_0.gguf new file mode 100644 index 0000000..bd05ec4 --- /dev/null +++ b/Llama-3.1-8b-ITA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b723e627fe340d4e62db277e36f7d81f1621a89fc95956ac569e60c14548f7d6 +size 8540771744 diff --git a/Llama-3.1-8b-ITA.f16.gguf b/Llama-3.1-8b-ITA.f16.gguf new file mode 100644 index 0000000..bc4dc94 --- /dev/null +++ b/Llama-3.1-8b-ITA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a147956d7a89a784ea9798889a2046144160905ff396f5b458a4ef30b1142154 +size 16068892064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9ddcc34 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: DeepMount00/Llama-3.1-8b-ITA +language: +- en +- it +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/DeepMount00/Llama-3.1-8b-ITA + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-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-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8b-ITA-GGUF/resolve/main/Llama-3.1-8b-ITA.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. + +