commit 361077cc81130426a249b2e7e6f42e9cae5f915e Author: ModelHub XC Date: Tue Jun 23 16:46:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d026f3f --- /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 +AV-FI-Qwen2.5-3B-PT-BR-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AV-FI-Qwen2.5-3B-PT-BR-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.IQ4_XS.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..35d5782 --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5537620170235aea5797ba2499a2f6b31a102e1973d108395e10181db7c5fcf8 +size 1753185120 diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q2_K.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q2_K.gguf new file mode 100644 index 0000000..da1ac81 --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a33eebd1031d62a166c8bd422387513c8298ed8b8af1d4747591ddb0a01d49d +size 1274755936 diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_L.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..709ff69 --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86a71978114dc2a53d9b7135d65c878690ee964b8180bb0bbf4792546b334aef +size 1707391840 diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_M.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b023a78 --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a612cb19ebfd77240633a25a31343b068b87c233bbdceb8c994d32aeec36cbc +size 1590475616 diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_S.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..78953c3 --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b01ebb4592ba73f1072ccec5ae443643d7a91e12434acd07b1579f9a777a026 +size 1454357344 diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_M.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f435aec --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c7f9d3f336a0357a5b4eee1a89055caa10522d39884db1d26daadd38dea9473 +size 1929902944 diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_S.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..24e3815 --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d2d8566296c14b5f620547862685d33c9087b703f8189441764ad815eff035 +size 1834384224 diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_M.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..91f0749 --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dd5dde30eaf0041bd0a3f4a3cca7e43d5f68d197dd9800b772e5d3079639282 +size 2224814944 diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_S.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..ea8d240 --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f21d989030453b3f97e867bab7a3f9124e69046a557f3389d62fa582508cde4 +size 2169666400 diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q6_K.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q6_K.gguf new file mode 100644 index 0000000..a6006a6 --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:802f9c25d9a3bee3048ae9f3e733f53f39427e62feaba71fd06124f7d67bc622 +size 2538158944 diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q8_0.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q8_0.gguf new file mode 100644 index 0000000..a95b981 --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d4794269d2122c4c9d2ebff7f8e10c85c834f5f1f4a90880bbbd111d4078075 +size 3285476192 diff --git a/AV-FI-Qwen2.5-3B-PT-BR-Instruct.f16.gguf b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.f16.gguf new file mode 100644 index 0000000..5580c76 --- /dev/null +++ b/AV-FI-Qwen2.5-3B-PT-BR-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d9eeb901c5f910fd8926a3594b8cdd6eb181b2ad22d67a436cbc3a8d090d47e +size 6178317152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..34ca24b --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: amadeusai/Amadeus-Verbo-FI-Qwen2.5-3B-PT-BR-Instruct +language: +- pt +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +--- +## About + + + + + + +static quants of https://huggingface.co/amadeusai/Amadeus-Verbo-FI-Qwen2.5-3B-PT-BR-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AV-FI-Qwen2.5-3B-PT-BR-Instruct-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/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AV-FI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-FI-Qwen2.5-3B-PT-BR-Instruct.f16.gguf) | f16 | 6.3 | 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. + +