commit a43155a4287f18a921c8b793bae2a9a428cd9c36 Author: ModelHub XC Date: Fri Jul 31 11:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..42d439a --- /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-Llama-2-7b-mix.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Llama-2-7b-mix.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Llama-2-7b-mix.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Llama-2-7b-mix.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Llama-2-7b-mix.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Llama-2-7b-mix.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Llama-2-7b-mix.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Llama-2-7b-mix.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Llama-2-7b-mix.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Llama-2-7b-mix.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Llama-2-7b-mix.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Llama-2-7b-mix.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Llama-2-7b-mix.IQ4_XS.gguf b/Llama-3.1-8B-Llama-2-7b-mix.IQ4_XS.gguf new file mode 100644 index 0000000..718f4d8 --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db1c3ec29e64f3dc110aabeb1ce7ad9c15da919f0293469e0c9467246d0a7015 +size 4484364064 diff --git a/Llama-3.1-8B-Llama-2-7b-mix.Q2_K.gguf b/Llama-3.1-8B-Llama-2-7b-mix.Q2_K.gguf new file mode 100644 index 0000000..2705dd5 --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be2052d3bdc3f1ca059d7ed237ad084288815629be05f4f60ec9d15417eb7eb2 +size 3179132704 diff --git a/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_L.gguf b/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_L.gguf new file mode 100644 index 0000000..9407a2b --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b637b60b34ff6ca86a4e9afbb7b15d1211a8c26014f7135c9e672c8667d2c7e +size 4321957664 diff --git a/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_M.gguf b/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_M.gguf new file mode 100644 index 0000000..f5fb7b7 --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:897d5d87766cfa199c440a76329d6f0a4a9d3f1373320477167b44d79a3711c1 +size 4018919200 diff --git a/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_S.gguf b/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_S.gguf new file mode 100644 index 0000000..6086be8 --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1937abd3d00c6004f271db9ef50d9255d75afc416acc2842ce1290a2f7eb3c +size 3664500512 diff --git a/Llama-3.1-8B-Llama-2-7b-mix.Q4_K_M.gguf b/Llama-3.1-8B-Llama-2-7b-mix.Q4_K_M.gguf new file mode 100644 index 0000000..dbf9453 --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2a6ae2286c63e8452c7c173c9568e2ea7855559530dac321e347ceafbf58fc +size 4920735520 diff --git a/Llama-3.1-8B-Llama-2-7b-mix.Q4_K_S.gguf b/Llama-3.1-8B-Llama-2-7b-mix.Q4_K_S.gguf new file mode 100644 index 0000000..223647b --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e71260c0c20474929cbd561b0e4265ec5148d049914aee5c2f48b8cd40691ce1 +size 4692670240 diff --git a/Llama-3.1-8B-Llama-2-7b-mix.Q5_K_M.gguf b/Llama-3.1-8B-Llama-2-7b-mix.Q5_K_M.gguf new file mode 100644 index 0000000..91e0801 --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8d20679455ead41491578747c3f6a65e0e3968600f8f49d2a6c049a89261792 +size 5732988704 diff --git a/Llama-3.1-8B-Llama-2-7b-mix.Q5_K_S.gguf b/Llama-3.1-8B-Llama-2-7b-mix.Q5_K_S.gguf new file mode 100644 index 0000000..ae878f9 --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfcb5ff65b6d3f8834c9b08adc3f5135aa30d6007f21e21e9fe30b7b04838670 +size 5599295264 diff --git a/Llama-3.1-8B-Llama-2-7b-mix.Q6_K.gguf b/Llama-3.1-8B-Llama-2-7b-mix.Q6_K.gguf new file mode 100644 index 0000000..6d0d817 --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42497482cd690080df987bb1f9286311ba6c541b610db1bbaa7ef86cfa710784 +size 6596007712 diff --git a/Llama-3.1-8B-Llama-2-7b-mix.Q8_0.gguf b/Llama-3.1-8B-Llama-2-7b-mix.Q8_0.gguf new file mode 100644 index 0000000..e012169 --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91bc5699342a02982068389e6022445579df337f7f83465b4f710488f8917c8d +size 8540772128 diff --git a/Llama-3.1-8B-Llama-2-7b-mix.f16.gguf b/Llama-3.1-8B-Llama-2-7b-mix.f16.gguf new file mode 100644 index 0000000..8acaa75 --- /dev/null +++ b/Llama-3.1-8B-Llama-2-7b-mix.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaacf5cd38378d2c5d1b8481b065c41bc4dbe9d5c991501c91fa73b59347f830 +size 16068892448 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3a4abc5 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/Llama-3.1-8B-Llama-2-7b-mix +language: +- en +library_name: transformers +model_name: Llama-3.1-8B-Llama-2-7b-mix +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-3.1-8B-Llama-2-7b-mix + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-Llama-2-7b-mix-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-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Llama-2-7b-mix-GGUF/resolve/main/Llama-3.1-8B-Llama-2-7b-mix.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. + +