commit 93ac543acd7a854e18d8b292b851ec676536233c Author: ModelHub XC Date: Tue Jul 7 02:20:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d204eb1 --- /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-3-8B-Dolphin-Portuguese.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Dolphin-Portuguese.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Dolphin-Portuguese.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Dolphin-Portuguese.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Dolphin-Portuguese.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Dolphin-Portuguese.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Dolphin-Portuguese.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Dolphin-Portuguese.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Dolphin-Portuguese.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Dolphin-Portuguese.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Dolphin-Portuguese.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Dolphin-Portuguese.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Dolphin-Portuguese.IQ4_XS.gguf b/Llama-3-8B-Dolphin-Portuguese.IQ4_XS.gguf new file mode 100644 index 0000000..55b5c7c --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd312da3fa4c4d6851a3285df7787ff6ae3658289f7e4e77514720c9e3b0a197 +size 4484363232 diff --git a/Llama-3-8B-Dolphin-Portuguese.Q2_K.gguf b/Llama-3-8B-Dolphin-Portuguese.Q2_K.gguf new file mode 100644 index 0000000..9211935 --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04b0676fe2f049e21069a44237b52fb0cf3c14963d8c8aaeaaf2e37a478e19c6 +size 3179131872 diff --git a/Llama-3-8B-Dolphin-Portuguese.Q3_K_L.gguf b/Llama-3-8B-Dolphin-Portuguese.Q3_K_L.gguf new file mode 100644 index 0000000..7581525 --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:809525085479c3d93043691544df0fad9870b8b157c3d0c310b76f05ce4356c0 +size 4321956832 diff --git a/Llama-3-8B-Dolphin-Portuguese.Q3_K_M.gguf b/Llama-3-8B-Dolphin-Portuguese.Q3_K_M.gguf new file mode 100644 index 0000000..831f7fa --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d27b65250860c826cb048a4a001c284ddbb17d0d42d3c216fff92c2dcc9c678e +size 4018918368 diff --git a/Llama-3-8B-Dolphin-Portuguese.Q3_K_S.gguf b/Llama-3-8B-Dolphin-Portuguese.Q3_K_S.gguf new file mode 100644 index 0000000..42d4fe4 --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c855584d32fa4d3739138b6cbfe512f0c567bad70792806c4df3f9604a631cb8 +size 3664499680 diff --git a/Llama-3-8B-Dolphin-Portuguese.Q4_K_M.gguf b/Llama-3-8B-Dolphin-Portuguese.Q4_K_M.gguf new file mode 100644 index 0000000..9da0d41 --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:576641edc4b7aefe3a460b73ca7604de29214072fb85f6b034442342a39c1545 +size 4920734688 diff --git a/Llama-3-8B-Dolphin-Portuguese.Q4_K_S.gguf b/Llama-3-8B-Dolphin-Portuguese.Q4_K_S.gguf new file mode 100644 index 0000000..2fb937a --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98cccd453d259490ea828869562c20b1d09b4a05ccf7e3301f9721437a14f4ef +size 4692669408 diff --git a/Llama-3-8B-Dolphin-Portuguese.Q5_K_M.gguf b/Llama-3-8B-Dolphin-Portuguese.Q5_K_M.gguf new file mode 100644 index 0000000..4ed1fab --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c12c404038d35567cbbe9df55e53471722d49cd401d3b7848f1b22a6d168519d +size 5732987872 diff --git a/Llama-3-8B-Dolphin-Portuguese.Q5_K_S.gguf b/Llama-3-8B-Dolphin-Portuguese.Q5_K_S.gguf new file mode 100644 index 0000000..9da74c3 --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9de9c1fa5801888d9660eacf7fc5bdae0c333698724551dd96e34fa45b775926 +size 5599294432 diff --git a/Llama-3-8B-Dolphin-Portuguese.Q6_K.gguf b/Llama-3-8B-Dolphin-Portuguese.Q6_K.gguf new file mode 100644 index 0000000..a3f3ded --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a468084ddecb9a36f9b868f38b6cd2fb9f6aeecc99073d4771a4f5c0f24b01 +size 6596006880 diff --git a/Llama-3-8B-Dolphin-Portuguese.Q8_0.gguf b/Llama-3-8B-Dolphin-Portuguese.Q8_0.gguf new file mode 100644 index 0000000..7709b71 --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2f0d5b5a4892d066cdd8cb4918c0d74fa73b911b82a8c0e28a193878c25155c +size 8540771296 diff --git a/Llama-3-8B-Dolphin-Portuguese.f16.gguf b/Llama-3-8B-Dolphin-Portuguese.f16.gguf new file mode 100644 index 0000000..379a241 --- /dev/null +++ b/Llama-3-8B-Dolphin-Portuguese.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93d95b88fbedbe7874780d355cf762705c19284a11ed0da5499b2bdfecdb8a3c +size 16068891616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8b1631a --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: adalbertojunior/Llama-3-8B-Dolphin-Portuguese +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/adalbertojunior/Llama-3-8B-Dolphin-Portuguese + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-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-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Dolphin-Portuguese-GGUF/resolve/main/Llama-3-8B-Dolphin-Portuguese.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. + +