commit 3d56f4c4289ede8fbbc02876fe9c2af075cfddd6 Author: ModelHub XC Date: Fri Oct 30 18:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e3827ae --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +llama3.1-airoboros3.2-QDT-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-airoboros3.2-QDT-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..522d4de --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: nbeerbower/llama3.1-airoboros3.2-QDT-8B +datasets: +- jondurbin/airoboros-3.2 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/nbeerbower/llama3.1-airoboros3.2-QDT-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-i1-GGUF +## 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/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-airoboros3.2-QDT-8B-GGUF/resolve/main/llama3.1-airoboros3.2-QDT-8B.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/llama3.1-airoboros3.2-QDT-8B.IQ3_M.gguf b/llama3.1-airoboros3.2-QDT-8B.IQ3_M.gguf new file mode 100644 index 0000000..1537955 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b832109d5e5c9633283fcd125eddcf97199d27a2ecd71c6c64f1fd3a18150512 +size 3784828704 diff --git a/llama3.1-airoboros3.2-QDT-8B.IQ3_S.gguf b/llama3.1-airoboros3.2-QDT-8B.IQ3_S.gguf new file mode 100644 index 0000000..b91ccfc --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6559535bd1b2ddd861131a0ed46b660608dd9ae5118954245884493f1f1db99c +size 3682330400 diff --git a/llama3.1-airoboros3.2-QDT-8B.IQ3_XS.gguf b/llama3.1-airoboros3.2-QDT-8B.IQ3_XS.gguf new file mode 100644 index 0000000..bdcee1d --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc8b3d1f8f08f72010a1e7c5acb3da7aa90e7af2fb77cfbde6f12f89051a877 +size 3518752544 diff --git a/llama3.1-airoboros3.2-QDT-8B.IQ4_XS.gguf b/llama3.1-airoboros3.2-QDT-8B.IQ4_XS.gguf new file mode 100644 index 0000000..bd38acb --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d9db3b2e015c7972c92cb85797c12aff6630ca44e1fe15955bcb22b7e436511 +size 4484368160 diff --git a/llama3.1-airoboros3.2-QDT-8B.Q2_K.gguf b/llama3.1-airoboros3.2-QDT-8B.Q2_K.gguf new file mode 100644 index 0000000..355749a --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd43f6781571e03dae7c02948da607435d2ef7985ef8d1ea23317620753353b +size 3179136800 diff --git a/llama3.1-airoboros3.2-QDT-8B.Q3_K_L.gguf b/llama3.1-airoboros3.2-QDT-8B.Q3_K_L.gguf new file mode 100644 index 0000000..1a867f0 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:380e0b813abb09272fda3a4415c44a47bfbe6803485f4f727bfb25362a187818 +size 4321961760 diff --git a/llama3.1-airoboros3.2-QDT-8B.Q3_K_M.gguf b/llama3.1-airoboros3.2-QDT-8B.Q3_K_M.gguf new file mode 100644 index 0000000..fa3ba9b --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e266f52dd00e66ad7b2a473f8778de366767f389be738960bc4a0e803d2b3676 +size 4018923296 diff --git a/llama3.1-airoboros3.2-QDT-8B.Q3_K_S.gguf b/llama3.1-airoboros3.2-QDT-8B.Q3_K_S.gguf new file mode 100644 index 0000000..954b6be --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1becda98a6a70c8b377e16072d0121b71a3d084a94acb57b88d6fb853b7a650c +size 3664504608 diff --git a/llama3.1-airoboros3.2-QDT-8B.Q4_K_M.gguf b/llama3.1-airoboros3.2-QDT-8B.Q4_K_M.gguf new file mode 100644 index 0000000..73c2fdd --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cdd608a0c012f09b6d624d2f10d1cbd8b1a466b2e549d6b82c05d425299a617 +size 4920739616 diff --git a/llama3.1-airoboros3.2-QDT-8B.Q4_K_S.gguf b/llama3.1-airoboros3.2-QDT-8B.Q4_K_S.gguf new file mode 100644 index 0000000..91e7f61 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23694e7daf7b097c9ab5b72e705c10005c0541dfff5ddc34af6d7bd053f5a67d +size 4692674336 diff --git a/llama3.1-airoboros3.2-QDT-8B.Q5_K_M.gguf b/llama3.1-airoboros3.2-QDT-8B.Q5_K_M.gguf new file mode 100644 index 0000000..1d5c78c --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9d8ca7d597619f4c16481600729d18e0228f1bacc2a573cf27ce21ba2dbc49d +size 5732992800 diff --git a/llama3.1-airoboros3.2-QDT-8B.Q5_K_S.gguf b/llama3.1-airoboros3.2-QDT-8B.Q5_K_S.gguf new file mode 100644 index 0000000..a5c8303 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53d22818a339cf0d7da10f86853512d064f470e981228823cc66ed4fc4b29dd2 +size 5599299360 diff --git a/llama3.1-airoboros3.2-QDT-8B.Q6_K.gguf b/llama3.1-airoboros3.2-QDT-8B.Q6_K.gguf new file mode 100644 index 0000000..b31c937 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c27cb06fd966fd1098f3e100beb8eafbd4b6f64d08f3d983ae2804c7b93a867 +size 6596011808 diff --git a/llama3.1-airoboros3.2-QDT-8B.Q8_0.gguf b/llama3.1-airoboros3.2-QDT-8B.Q8_0.gguf new file mode 100644 index 0000000..93b78b8 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bddbd2d5fc2f2ed80aab51042729bdd981d72c407ea1b3d3930cd1cc2cef44cf +size 8540776224 diff --git a/llama3.1-airoboros3.2-QDT-8B.f16.gguf b/llama3.1-airoboros3.2-QDT-8B.f16.gguf new file mode 100644 index 0000000..af53ae8 --- /dev/null +++ b/llama3.1-airoboros3.2-QDT-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c49d08050e201cee53f2175053d0f0368bd58ed0499ee9b24a5e6f8f89f8369 +size 16068896544