commit 5ac9669ad122e7597ba61d4b0d38754dbcffc007 Author: ModelHub XC Date: Thu Jun 18 03:09:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-8b-quizgen-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0ff8bb5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-quizgen-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-quizgen-instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ff62002 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: jazzysnake01/llama-3-8b-quizgen-instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/jazzysnake01/llama-3-8b-quizgen-instruct + + +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-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-quizgen-instruct-GGUF/resolve/main/llama-3-8b-quizgen-instruct.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-3-8b-quizgen-instruct.IQ4_XS.gguf b/llama-3-8b-quizgen-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..1730169 --- /dev/null +++ b/llama-3-8b-quizgen-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f55f51f04d5d128e2e1b83ffaca9db11ad9aaf16726277d615dcb620db4e4000 +size 4484363296 diff --git a/llama-3-8b-quizgen-instruct.Q2_K.gguf b/llama-3-8b-quizgen-instruct.Q2_K.gguf new file mode 100644 index 0000000..43406af --- /dev/null +++ b/llama-3-8b-quizgen-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:721051197b716eb93e13c527fef864e513831b7d085d57070386907c49d4b440 +size 3179131936 diff --git a/llama-3-8b-quizgen-instruct.Q3_K_L.gguf b/llama-3-8b-quizgen-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..f7a1b54 --- /dev/null +++ b/llama-3-8b-quizgen-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d55109e43a53e69130112942f42e2d0239395466e77199625e951b0bb44635ec +size 4321956896 diff --git a/llama-3-8b-quizgen-instruct.Q3_K_M.gguf b/llama-3-8b-quizgen-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..d1efc1e --- /dev/null +++ b/llama-3-8b-quizgen-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74794a99c749c11e181abed7167c01de717caded7586f1d7e59413e9cc3f38fa +size 4018918432 diff --git a/llama-3-8b-quizgen-instruct.Q3_K_S.gguf b/llama-3-8b-quizgen-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..61be0bd --- /dev/null +++ b/llama-3-8b-quizgen-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e38b7b03769ea7d766eebf439a664facf151575353370dce73759e58f8369df +size 3664499744 diff --git a/llama-3-8b-quizgen-instruct.Q4_0_4_4.gguf b/llama-3-8b-quizgen-instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..cae7446 --- /dev/null +++ b/llama-3-8b-quizgen-instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e1b2be01806d984e96b63765da56fa69713acd5486d190ee1b9ab82b2782b98 +size 4661212192 diff --git a/llama-3-8b-quizgen-instruct.Q4_K_M.gguf b/llama-3-8b-quizgen-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..bd3e656 --- /dev/null +++ b/llama-3-8b-quizgen-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2500598f64af51c325dd0effc99b248e4609c0bb5c5f62c5898004c5a97c9575 +size 4920734752 diff --git a/llama-3-8b-quizgen-instruct.Q4_K_S.gguf b/llama-3-8b-quizgen-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..f34584b --- /dev/null +++ b/llama-3-8b-quizgen-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae6200dc2fdc5a3342df256d7b83139a6523a724e28938576e052479ecfc729d +size 4692669472 diff --git a/llama-3-8b-quizgen-instruct.Q5_K_M.gguf b/llama-3-8b-quizgen-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..beba378 --- /dev/null +++ b/llama-3-8b-quizgen-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1acb4c73e6481255b798ae0c0be1b1a5bf772b2da139bbd5f5cb5833135a0555 +size 5732987936 diff --git a/llama-3-8b-quizgen-instruct.Q5_K_S.gguf b/llama-3-8b-quizgen-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..24399d0 --- /dev/null +++ b/llama-3-8b-quizgen-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27cbbe44f44eb9ead32e1c6e103e878d31a1a4f53e395e37e71a0d21d03bf084 +size 5599294496 diff --git a/llama-3-8b-quizgen-instruct.Q6_K.gguf b/llama-3-8b-quizgen-instruct.Q6_K.gguf new file mode 100644 index 0000000..bd4790f --- /dev/null +++ b/llama-3-8b-quizgen-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fb98f3ab96b52ac17d0d8114491b169be3057a1f1cfafdf5851be764fb34a16 +size 6596006944 diff --git a/llama-3-8b-quizgen-instruct.Q8_0.gguf b/llama-3-8b-quizgen-instruct.Q8_0.gguf new file mode 100644 index 0000000..b6c0cd0 --- /dev/null +++ b/llama-3-8b-quizgen-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8844f90c0be6184eb2a38edf92cb2051ae1a8474240fad019ca876f51c17cbb6 +size 8540771360 diff --git a/llama-3-8b-quizgen-instruct.f16.gguf b/llama-3-8b-quizgen-instruct.f16.gguf new file mode 100644 index 0000000..3298158 --- /dev/null +++ b/llama-3-8b-quizgen-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b43e453fcf540caa6ff5267010763fb2f6e7a2b542259349d70956de335863a0 +size 16068891680