commit d3e4841de7d5ef76ed237161456d8a38bc4cc3ab Author: ModelHub XC Date: Tue Aug 4 13:23:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..37dfde1 --- /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-Instruct-Portuguese-v0.3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Portuguese-v0.3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Portuguese-v0.3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Portuguese-v0.3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Portuguese-v0.3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Portuguese-v0.3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Portuguese-v0.3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Portuguese-v0.3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Portuguese-v0.3.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.IQ4_XS.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.IQ4_XS.gguf new file mode 100644 index 0000000..56d212e --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad2a3b67a3ed6c4dac7f3f3f783e88a4143cad14a78939ef420224fce678bcb8 +size 4484367520 diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.Q2_K.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.Q2_K.gguf new file mode 100644 index 0000000..11a0013 --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3273bdca6499f830f46667989809032b0dd0cf6c68b62dc8015af36f190754d +size 3179136160 diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_L.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_L.gguf new file mode 100644 index 0000000..9ce17f5 --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1741546cfcd272572b7dd37c1e8f70f9f6d5510e831e3a1cf081389d648ca24 +size 4321961120 diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_M.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_M.gguf new file mode 100644 index 0000000..8b9b1e7 --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba405bde675c4be4fc59addd990cd35394243b7aabc53b3c0d195bcc4823260 +size 4018922656 diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_S.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_S.gguf new file mode 100644 index 0000000..3d67fc9 --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:241387805446090fea0ff15602909527e113184c7c6874da9498f5becfd52573 +size 3664503968 diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.Q4_K_M.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.Q4_K_M.gguf new file mode 100644 index 0000000..4c4fa67 --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ad4ae312905d84b77a77fc528c5c5a9e5111941ee490b5d97c725167c8a39b1 +size 4920738976 diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.Q4_K_S.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.Q4_K_S.gguf new file mode 100644 index 0000000..201527c --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99a4e073214039b37020431c302389610acb512534ea5f5d64ddf146c8c5ec44 +size 4692673696 diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.Q5_K_M.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.Q5_K_M.gguf new file mode 100644 index 0000000..6fe3418 --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ad5a2014d210997a3e557a2772cb0134709a039a77ce3466622457ae419bf55 +size 5732992160 diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.Q5_K_S.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.Q5_K_S.gguf new file mode 100644 index 0000000..e571997 --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdaa2710fb3a54f84993456c8805d950f19646a9737c8605eb3017566cb227ef +size 5599298720 diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.Q6_K.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.Q6_K.gguf new file mode 100644 index 0000000..4aa7c9e --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d54d6267583bc84f2d25de4cb04c1a0bc7c52e3c9da1e41a430356c6a0d0955 +size 6596011168 diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.Q8_0.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.Q8_0.gguf new file mode 100644 index 0000000..88f6f09 --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2918db0d3a08c534e3cc1ef1d065a5b4eef75f5cbf8d7777f06d25437d75eed +size 8540775584 diff --git a/Llama-3-8B-Instruct-Portuguese-v0.3.f16.gguf b/Llama-3-8B-Instruct-Portuguese-v0.3.f16.gguf new file mode 100644 index 0000000..77057e3 --- /dev/null +++ b/Llama-3-8B-Instruct-Portuguese-v0.3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29ea05a365d560bb355e18799d4f6ce2da1ab82f9e55fdb5422bc37b31fafe41 +size 16068895904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f77977b --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.3 +datasets: +- adalbertojunior/openHermes_portuguese +language: +- pt +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.3 + + +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-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Portuguese-v0.3-GGUF/resolve/main/Llama-3-8B-Instruct-Portuguese-v0.3.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. + +