commit a33777ac07445d2daf1f6347940e206851512ce7 Author: ModelHub XC Date: Tue Jun 2 20:56:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-8b-vietnamese-qa-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..99a5a69 --- /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-vietnamese-qa.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-vietnamese-qa.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-vietnamese-qa.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-vietnamese-qa.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-vietnamese-qa.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-vietnamese-qa.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-vietnamese-qa.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-vietnamese-qa.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-vietnamese-qa.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-vietnamese-qa.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-vietnamese-qa.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-vietnamese-qa.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3dcbf26 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: hieuducle/llama-3.1-8b-vietnamese-qa +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/hieuducle/llama-3.1-8b-vietnamese-qa + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.1-8b-vietnamese-qa-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/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-vietnamese-qa-GGUF/resolve/main/llama-3.1-8b-vietnamese-qa.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. + + diff --git a/llama-3.1-8b-vietnamese-qa.IQ4_XS.gguf b/llama-3.1-8b-vietnamese-qa.IQ4_XS.gguf new file mode 100644 index 0000000..31b7357 --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db2d6e67b9fcb95b5cb1972bb4fb5373bd00781bcb5a3bba6224f63a47fd5582 +size 4484368384 diff --git a/llama-3.1-8b-vietnamese-qa.Q2_K.gguf b/llama-3.1-8b-vietnamese-qa.Q2_K.gguf new file mode 100644 index 0000000..078485b --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7110c598d01e7e93bfe486419db59ff83c6e23702c31b7bd0bd58923654dcc60 +size 3179137024 diff --git a/llama-3.1-8b-vietnamese-qa.Q3_K_L.gguf b/llama-3.1-8b-vietnamese-qa.Q3_K_L.gguf new file mode 100644 index 0000000..e4582cc --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24924c803cd73167c96f47b9dacf3b343f3f6d12f7537eb2c4644d10a2f8dbd2 +size 4321961984 diff --git a/llama-3.1-8b-vietnamese-qa.Q3_K_M.gguf b/llama-3.1-8b-vietnamese-qa.Q3_K_M.gguf new file mode 100644 index 0000000..d31892b --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f7fea858d06d5851f135a1cb2439adc610b315170ef2da7945ec314ef402823 +size 4018923520 diff --git a/llama-3.1-8b-vietnamese-qa.Q3_K_S.gguf b/llama-3.1-8b-vietnamese-qa.Q3_K_S.gguf new file mode 100644 index 0000000..78c8e1e --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:130ab97872c3e817d24155894c850efb836b9d189c582b13346873c25953d20f +size 3664504832 diff --git a/llama-3.1-8b-vietnamese-qa.Q4_K_M.gguf b/llama-3.1-8b-vietnamese-qa.Q4_K_M.gguf new file mode 100644 index 0000000..2ef1d51 --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a405abb8947405cbc3a58e24a58b3ff9e9d287226013fbe6258114d3c66426 +size 4920739840 diff --git a/llama-3.1-8b-vietnamese-qa.Q4_K_S.gguf b/llama-3.1-8b-vietnamese-qa.Q4_K_S.gguf new file mode 100644 index 0000000..4740d45 --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22daae014dedc404d6804ac2c16ff8dd4f37bd0172031ddc86e91a6c24f01538 +size 4692674560 diff --git a/llama-3.1-8b-vietnamese-qa.Q5_K_M.gguf b/llama-3.1-8b-vietnamese-qa.Q5_K_M.gguf new file mode 100644 index 0000000..8d503c1 --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f13d17cc4d58546d75056b258abd1b52eccd9a172f42f12d35bdc86ed91c94f4 +size 5732993024 diff --git a/llama-3.1-8b-vietnamese-qa.Q5_K_S.gguf b/llama-3.1-8b-vietnamese-qa.Q5_K_S.gguf new file mode 100644 index 0000000..e258168 --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5be7b6301da51ad5fa264d7a042df46a78150297aa5257d9d0b75267352c4a23 +size 5599299584 diff --git a/llama-3.1-8b-vietnamese-qa.Q6_K.gguf b/llama-3.1-8b-vietnamese-qa.Q6_K.gguf new file mode 100644 index 0000000..9385a91 --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:587d24056faf4ac2eb16b84f184f32e34721de2f2c64015c1953a037109070dd +size 6596012032 diff --git a/llama-3.1-8b-vietnamese-qa.Q8_0.gguf b/llama-3.1-8b-vietnamese-qa.Q8_0.gguf new file mode 100644 index 0000000..685afbc --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44a253e8256ccfa8bdd7370bc391216b1379fb0660c12caca5dcc8ba3815ffa1 +size 8540776448 diff --git a/llama-3.1-8b-vietnamese-qa.f16.gguf b/llama-3.1-8b-vietnamese-qa.f16.gguf new file mode 100644 index 0000000..2f58394 --- /dev/null +++ b/llama-3.1-8b-vietnamese-qa.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:537c8f2ef16d72a8fbb863099884c1cf051ce433bf291ca90c0bf6b8a122dd79 +size 16068896768