commit b08080ad6ceca326b414c27e882a5f712b7c8bbd Author: ModelHub XC Date: Wed Jun 24 21:20:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLaMA3-8b-CQA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ec90cf2 --- /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 +LLaMA3-8b-CQA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-8b-CQA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-8b-CQA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-8b-CQA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-8b-CQA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-8b-CQA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-8b-CQA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-8b-CQA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-8b-CQA.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-8b-CQA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-8b-CQA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-8b-CQA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMA3-8b-CQA.IQ4_XS.gguf b/LLaMA3-8b-CQA.IQ4_XS.gguf new file mode 100644 index 0000000..2001cc1 --- /dev/null +++ b/LLaMA3-8b-CQA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:678d4301eb11b875273c62379edeb514b0492e73b31e960e9ff46d9b3f3451cb +size 4484363200 diff --git a/LLaMA3-8b-CQA.Q2_K.gguf b/LLaMA3-8b-CQA.Q2_K.gguf new file mode 100644 index 0000000..56a7338 --- /dev/null +++ b/LLaMA3-8b-CQA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba44f65b8c6659d967cb12bffb2165bab488c5021ba53fda36e23bd588a5307 +size 3179131840 diff --git a/LLaMA3-8b-CQA.Q3_K_L.gguf b/LLaMA3-8b-CQA.Q3_K_L.gguf new file mode 100644 index 0000000..347c855 --- /dev/null +++ b/LLaMA3-8b-CQA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab1ca1a227fb691977e30a9009a651a6ea4878c47d2dc5c335762652b737095 +size 4321956800 diff --git a/LLaMA3-8b-CQA.Q3_K_M.gguf b/LLaMA3-8b-CQA.Q3_K_M.gguf new file mode 100644 index 0000000..5cf450e --- /dev/null +++ b/LLaMA3-8b-CQA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6843665ce0530394d9af3646bf1ff5e7bedd06f29ebef5a27518ac2fa2c2569 +size 4018918336 diff --git a/LLaMA3-8b-CQA.Q3_K_S.gguf b/LLaMA3-8b-CQA.Q3_K_S.gguf new file mode 100644 index 0000000..dbda8ee --- /dev/null +++ b/LLaMA3-8b-CQA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2054b76664a8ce2f6ca343ff4be02df5beebd81ea1016e48fc2808baf99998a +size 3664499648 diff --git a/LLaMA3-8b-CQA.Q4_K_M.gguf b/LLaMA3-8b-CQA.Q4_K_M.gguf new file mode 100644 index 0000000..fdbc9c6 --- /dev/null +++ b/LLaMA3-8b-CQA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a15c1348d3e867e1273ac86006c62e73178210cb2cfe3cb6fe19ae507f2046a8 +size 4920734656 diff --git a/LLaMA3-8b-CQA.Q4_K_S.gguf b/LLaMA3-8b-CQA.Q4_K_S.gguf new file mode 100644 index 0000000..d8f8d99 --- /dev/null +++ b/LLaMA3-8b-CQA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3799a464c3fb27b66843da8897c3cdffe3a3f1d327882a259b764792ebe48db +size 4692669376 diff --git a/LLaMA3-8b-CQA.Q5_K_M.gguf b/LLaMA3-8b-CQA.Q5_K_M.gguf new file mode 100644 index 0000000..b146bf9 --- /dev/null +++ b/LLaMA3-8b-CQA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5920665f9ee9bbbaf1083ad6f4e52d64818e852ec3367b11d155f073009fa6ed +size 5732987840 diff --git a/LLaMA3-8b-CQA.Q5_K_S.gguf b/LLaMA3-8b-CQA.Q5_K_S.gguf new file mode 100644 index 0000000..ca4b73a --- /dev/null +++ b/LLaMA3-8b-CQA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68555bd407de3a1a6b8c93d3407a443506ba1dc65c0cdf889d9116730983de08 +size 5599294400 diff --git a/LLaMA3-8b-CQA.Q6_K.gguf b/LLaMA3-8b-CQA.Q6_K.gguf new file mode 100644 index 0000000..e7255b3 --- /dev/null +++ b/LLaMA3-8b-CQA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f51d07fdd07cbc82d38516de28d5da00b3ca2e52d7e03198367b3e36c0564290 +size 6596006848 diff --git a/LLaMA3-8b-CQA.Q8_0.gguf b/LLaMA3-8b-CQA.Q8_0.gguf new file mode 100644 index 0000000..2444798 --- /dev/null +++ b/LLaMA3-8b-CQA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce0b2b210a18819fcd42a9dc858b5b543d1d028a61563e8be507b944c971f73 +size 8540771264 diff --git a/LLaMA3-8b-CQA.f16.gguf b/LLaMA3-8b-CQA.f16.gguf new file mode 100644 index 0000000..6f4a3c3 --- /dev/null +++ b/LLaMA3-8b-CQA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9adc039ca3c84d0f96931877d9bcade2e3f5ec998d6349994c3261a50ecc2a2 +size 16068891584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6e49cdb --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: VityaVitalich/LLaMA3-8b-CQA +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/VityaVitalich/LLaMA3-8b-CQA + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LLaMA3-8b-CQA-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/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-8b-CQA-GGUF/resolve/main/LLaMA3-8b-CQA.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. + +