commit eeda540e93e9645eebc12655e92b70771cd872e3 Author: ModelHub XC Date: Thu Oct 8 06:31:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/JA-Llama-3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..af4d874 --- /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 +JA-Llama-3.f16.gguf filter=lfs diff=lfs merge=lfs -text +JA-Llama-3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JA-Llama-3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +JA-Llama-3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +JA-Llama-3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +JA-Llama-3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JA-Llama-3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JA-Llama-3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +JA-Llama-3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JA-Llama-3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JA-Llama-3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JA-Llama-3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/JA-Llama-3.IQ4_XS.gguf b/JA-Llama-3.IQ4_XS.gguf new file mode 100644 index 0000000..d23fd1a --- /dev/null +++ b/JA-Llama-3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad9f2774c94818a07cae972c01cc2ecfa5041b6ebc721c81b93eddd42c3fe530 +size 4591812416 diff --git a/JA-Llama-3.Q2_K.gguf b/JA-Llama-3.Q2_K.gguf new file mode 100644 index 0000000..ad87e3e --- /dev/null +++ b/JA-Llama-3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00644401ded87f556c7feb503ffb79421072d9402cbeacbd9c383a6e23af0cf1 +size 3280470784 diff --git a/JA-Llama-3.Q3_K_L.gguf b/JA-Llama-3.Q3_K_L.gguf new file mode 100644 index 0000000..a4e69a9 --- /dev/null +++ b/JA-Llama-3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea381679612baa2557e853e217346077a1674f8b9b1407daf786a9815f639d9 +size 4430020896 diff --git a/JA-Llama-3.Q3_K_M.gguf b/JA-Llama-3.Q3_K_M.gguf new file mode 100644 index 0000000..abe091e --- /dev/null +++ b/JA-Llama-3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c77f86474ae225c7e4c39bd8f82eb1665603bea1a685432bef528dff84a454 +size 4122788128 diff --git a/JA-Llama-3.Q3_K_S.gguf b/JA-Llama-3.Q3_K_S.gguf new file mode 100644 index 0000000..f8e35c7 --- /dev/null +++ b/JA-Llama-3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d8008ba56deae4aa0dbc58a0a874d7521fd6f3207ccb3dbafb09a6d1b356b53 +size 3768238368 diff --git a/JA-Llama-3.Q4_K_M.gguf b/JA-Llama-3.Q4_K_M.gguf new file mode 100644 index 0000000..04911af --- /dev/null +++ b/JA-Llama-3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ade330ffce2a9f8267c50ef2a4699cf380e137651d7e00bdc11d94ba18dfcc +size 5026265536 diff --git a/JA-Llama-3.Q4_K_S.gguf b/JA-Llama-3.Q4_K_S.gguf new file mode 100644 index 0000000..5af0299 --- /dev/null +++ b/JA-Llama-3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84cac7649b25a875f11c833cff1130ef8f14b4ada63157c35dae1b3cd8767e09 +size 4800494016 diff --git a/JA-Llama-3.Q5_K_M.gguf b/JA-Llama-3.Q5_K_M.gguf new file mode 100644 index 0000000..e11e071 --- /dev/null +++ b/JA-Llama-3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93a2d6870508334f1481ca01fd668449c7052be30b36739a1b2459c77dd2bb95 +size 5849457600 diff --git a/JA-Llama-3.Q5_K_S.gguf b/JA-Llama-3.Q5_K_S.gguf new file mode 100644 index 0000000..ec5d87f --- /dev/null +++ b/JA-Llama-3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faaae7239755efa095c9994fac7ed99411ac1a4f3485496d8606eb8198c170ed +size 5719106496 diff --git a/JA-Llama-3.Q6_K.gguf b/JA-Llama-3.Q6_K.gguf new file mode 100644 index 0000000..38f7086 --- /dev/null +++ b/JA-Llama-3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f042549870169918f0ef8b8d2bb8ff13e9143c7bb8e520c15ba9ff356e65dd29 +size 6724099168 diff --git a/JA-Llama-3.Q8_0.gguf b/JA-Llama-3.Q8_0.gguf new file mode 100644 index 0000000..f174200 --- /dev/null +++ b/JA-Llama-3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73634ec7639d5519d563911d98256853a834a4a0b4a13123192a40177232db23 +size 8707188512 diff --git a/JA-Llama-3.f16.gguf b/JA-Llama-3.f16.gguf new file mode 100644 index 0000000..883cb6f --- /dev/null +++ b/JA-Llama-3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5f0dfd2ba5f1bf76ea69dd9a835f65284ec2be7e4d3148a53bd4d5821fae91 +size 16383663392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5ce2be2 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: MartinJYHuang/JA-Llama-3 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/MartinJYHuang/JA-Llama-3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#JA-Llama-3-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/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/JA-Llama-3-GGUF/resolve/main/JA-Llama-3.f16.gguf) | f16 | 16.5 | 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. + +