commit ea7c80f2d9249c30e26d62537a20452ed8303bff Author: ModelHub XC Date: Mon Sep 7 10:10:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ba70f6 --- /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-3-8b-Instruct-OpenHermes-2.5-QLoRA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..90b2de9 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: yaystevek/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA +datasets: +- teknium/OpenHermes-2.5 +language: +- en +library_name: transformers +license: other +license_name: llama3 +quantized_by: mradermacher +tags: +- unsloth +- facebook +- meta +- pytorch +- llama +- llama-3 +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/yaystevek/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA + + +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-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA-GGUF/resolve/main/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.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-Instruct-OpenHermes-2.5-QLoRA.IQ4_XS.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.IQ4_XS.gguf new file mode 100644 index 0000000..1b2ee19 --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34799d998c67b5d031f73dd7f831fcd076f2934c193f40965346f64fc8ef5327 +size 4484364448 diff --git a/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q2_K.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q2_K.gguf new file mode 100644 index 0000000..d16c223 --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a217aaf971d6263763da02b477eff763502979ce1c4f1122a4e4adfaacbd430 +size 3179133088 diff --git a/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_L.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_L.gguf new file mode 100644 index 0000000..546f6f5 --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:129252aae4351f5f8bb625cceae1a97bb73c6b33da94ebd219053174145ff30e +size 4321958048 diff --git a/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_M.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_M.gguf new file mode 100644 index 0000000..c0b842e --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7969168559a626db90de4a396bcaae361d9e5e090b6b98d6e038003bb50d6a0d +size 4018919584 diff --git a/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_S.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_S.gguf new file mode 100644 index 0000000..06fd609 --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:463d7365d62796c629f6836f26ab8d62c536607f1b3d67c69879437589e7bdf5 +size 3664500896 diff --git a/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q4_K_M.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q4_K_M.gguf new file mode 100644 index 0000000..07d89b4 --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9464346e9a5afa4a24083c7a0ca4f94483aed78dad7be469268fcff8e5effa8e +size 4920735904 diff --git a/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q4_K_S.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q4_K_S.gguf new file mode 100644 index 0000000..d111091 --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:221457e77803180ad55e2da3b0bd3c39a89f28b7d93aa2239019cbde12e08f16 +size 4692670624 diff --git a/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q5_K_M.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q5_K_M.gguf new file mode 100644 index 0000000..1d96156 --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b269d44a75e71de6b76cd9d095499ea01f53ecd68d3f8d5504cf2289106da9fc +size 5732989088 diff --git a/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q5_K_S.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q5_K_S.gguf new file mode 100644 index 0000000..953ab17 --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa536164e384034afd74409a1c5c4abfbb317fc35c2ca21e4d4c6989e612250d +size 5599295648 diff --git a/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q6_K.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q6_K.gguf new file mode 100644 index 0000000..8e68840 --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7e18ae9f88fab37c444ae666f7c3f39051a17dde1fbaf51b8d8b57de958e8cd +size 6596008096 diff --git a/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q8_0.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q8_0.gguf new file mode 100644 index 0000000..7d6a11f --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ef8656d113575efef20242a17bbb0d3c146e866a0c26bd8142f8d2b244a551 +size 8540772512 diff --git a/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.f16.gguf b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.f16.gguf new file mode 100644 index 0000000..3654a58 --- /dev/null +++ b/llama-3-8b-Instruct-OpenHermes-2.5-QLoRA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98bf40f33f256ca5e85ce9840ea1947cef3b853666f1430338af9fba1be568c6 +size 16068892832