commit cc3e790d9e6be800818d22f1d123ddc6b03ac577 Author: ModelHub XC Date: Sat Jun 13 03:16:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b711590 --- /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 +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.f16.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-vietnamese-r16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.IQ4_XS.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.IQ4_XS.gguf new file mode 100644 index 0000000..3f70668 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f71e21e3472054274e5c46bb5fc8f585ce20ba17fce72fb0e63ebcc7a367f87b +size 4484368736 diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q2_K.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q2_K.gguf new file mode 100644 index 0000000..1e18dde --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e5d3d821bd7f1f2afccaf764b897178b2bf58ac738e6e8b9ee5496db76f3d62 +size 3179137376 diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_L.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_L.gguf new file mode 100644 index 0000000..9835f11 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb80dc7e0564e04aed7efbb7afcdab55bcad980f7507a8ccb5d59c326fa7b0ff +size 4321962336 diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_M.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_M.gguf new file mode 100644 index 0000000..cc3e081 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:864208bb7dbb58ac82bfdbcf3fcd3c4aee23301a323d5fbeef0da52bea36d8ec +size 4018923872 diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_S.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_S.gguf new file mode 100644 index 0000000..fd0d380 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3005609588e169db2f9416d375b0ec39dda4020d7aa0a5dbbeffe9db1523b756 +size 3664505184 diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q4_K_M.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q4_K_M.gguf new file mode 100644 index 0000000..b91dc5a --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2209e85c0e7daca8e467d2f774c258f6b4e60a554987ee8318efc8d7c2afc23 +size 4920740192 diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q4_K_S.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q4_K_S.gguf new file mode 100644 index 0000000..542800c --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa946db1854c5ac11ee28dc8fe59fabec499c02d2d31ef87299e343d02e611a1 +size 4692674912 diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q5_K_M.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q5_K_M.gguf new file mode 100644 index 0000000..671178e --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ea2875dcad033559259c512a92263fff187eff82d4d2c4208cfeb37773f82eb +size 5732993376 diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q5_K_S.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q5_K_S.gguf new file mode 100644 index 0000000..1102793 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce303bcff7d11fddc594e144cac9b21a6ccde9ef9c41474bd4cdab0c42b06ea3 +size 5599299936 diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q6_K.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q6_K.gguf new file mode 100644 index 0000000..e6e1380 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00e67aea22549f5b203f821f02d823cb2359f9652ef753dec2da0e3bafd4bbb5 +size 6596012384 diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q8_0.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q8_0.gguf new file mode 100644 index 0000000..0e68055 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9dac90b2edd2af901966652a68024ab23014ef120108e80bad21637428928df +size 8540776800 diff --git a/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.f16.gguf b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.f16.gguf new file mode 100644 index 0000000..44ddc51 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d5a6e97f89ebcaaf59420c38762d277ea230da5b023bc69b2b7981248e4b3d9 +size 16068897120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7a8330e --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: DataOpsFusion/Meta-Llama-3.1-8B-Instruct-vietnamese-r16 +datasets: +- hoanghai2110/vietnamese-dataset +language: +- vi +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama3 +- vietnamese +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DataOpsFusion/Meta-Llama-3.1-8B-Instruct-vietnamese-r16 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Meta-Llama-3.1-8B-Instruct-vietnamese-r16-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/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-vietnamese-r16-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-vietnamese-r16.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. + +