commit 1c4f2ba35e6753829df2f0259967c93be97bc960 Author: ModelHub XC Date: Mon Sep 14 14:22:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..779a87e --- /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 +Hermes-3-Llama-3.1-8B-lorablated.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.f16.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.1-8B-lorablated.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hermes-3-Llama-3.1-8B-lorablated.IQ3_M.gguf b/Hermes-3-Llama-3.1-8B-lorablated.IQ3_M.gguf new file mode 100644 index 0000000..dee378d --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb241d1083bc7002c0c5c91550121dec1fdfbfdbf74d5f8f28906cc29547f21 +size 3784823648 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.IQ3_S.gguf b/Hermes-3-Llama-3.1-8B-lorablated.IQ3_S.gguf new file mode 100644 index 0000000..2831118 --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02328aa88e4a88357439b14943801f620039aedb86711c91c8a05686431e042a +size 3682325344 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.IQ3_XS.gguf b/Hermes-3-Llama-3.1-8B-lorablated.IQ3_XS.gguf new file mode 100644 index 0000000..896e0a9 --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e733ceaaee9fdfde36f9e773dfd05826cbaf99d9054ea3f813322bdf0c4402 +size 3518747488 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.IQ4_XS.gguf b/Hermes-3-Llama-3.1-8B-lorablated.IQ4_XS.gguf new file mode 100644 index 0000000..1a6d1eb --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:609f8002b565dfc68e27be82f071cd457a9065e613bd6e1846f364dcb74bea81 +size 4484363104 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.Q2_K.gguf b/Hermes-3-Llama-3.1-8B-lorablated.Q2_K.gguf new file mode 100644 index 0000000..b4d7a72 --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90510498040cada10bbaf64400f4be8190f535679b5564671407e6017d353d01 +size 3179131744 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_L.gguf b/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_L.gguf new file mode 100644 index 0000000..3efc582 --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0da91560b5b135ddd4f5e6ce7a513ebd153237f5038d64fa072269e817298cf9 +size 4321956704 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_M.gguf b/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_M.gguf new file mode 100644 index 0000000..966adbb --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e34560734d2f9e690ff3c4b21e7cbd97862cd8e1bdd04aa118273a656f3fa269 +size 4018918240 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_S.gguf b/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_S.gguf new file mode 100644 index 0000000..985e662 --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:596e7ef5801edf6d5e30f4aeb583b741eeacb128a413959c09cb27284b564a02 +size 3664499552 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.Q4_K_M.gguf b/Hermes-3-Llama-3.1-8B-lorablated.Q4_K_M.gguf new file mode 100644 index 0000000..3c13622 --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a0ca04f4a022d3500b879c7f78d6a3dee2b50dd6e11785467e204e60cfd50b1 +size 4920734560 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.Q4_K_S.gguf b/Hermes-3-Llama-3.1-8B-lorablated.Q4_K_S.gguf new file mode 100644 index 0000000..650221d --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:393662875a1e0fc217887f9b09c27577b95f4a9f684c0335354aaf92958fa28f +size 4692669280 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.Q5_K_M.gguf b/Hermes-3-Llama-3.1-8B-lorablated.Q5_K_M.gguf new file mode 100644 index 0000000..d51d949 --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3d640b860eb68b098782506d70f6c6d900c3f8a6ecccabd79a0916d53a5c0df +size 5732987744 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.Q5_K_S.gguf b/Hermes-3-Llama-3.1-8B-lorablated.Q5_K_S.gguf new file mode 100644 index 0000000..a2502d9 --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36062cfa0f7524c2bab31306e93e35715bf2dd0d46cc3deaae2b1458e8ae71b9 +size 5599294304 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.Q6_K.gguf b/Hermes-3-Llama-3.1-8B-lorablated.Q6_K.gguf new file mode 100644 index 0000000..3cbafd8 --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a660608bf2b5a4864250cc8ddc2fb9ebe4747d0b7f2f63c7b9a1eb7d6c67f5 +size 6596006752 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.Q8_0.gguf b/Hermes-3-Llama-3.1-8B-lorablated.Q8_0.gguf new file mode 100644 index 0000000..c3e90b0 --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0835f14cb4712f4959a4a832eab86c9e4a764f03adfd7d1ed48b4f86bb489d16 +size 8540771168 diff --git a/Hermes-3-Llama-3.1-8B-lorablated.f16.gguf b/Hermes-3-Llama-3.1-8B-lorablated.f16.gguf new file mode 100644 index 0000000..6dbe627 --- /dev/null +++ b/Hermes-3-Llama-3.1-8B-lorablated.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d4e8deb9c73e5d01b18f9408251d19653162aebb1925db209537150203808a +size 16068891488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ca43a96 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: mlabonne/Hermes-3-Llama-3.1-8B-lorablated +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mlabonne/Hermes-3-Llama-3.1-8B-lorablated + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-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/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-8B-lorablated-GGUF/resolve/main/Hermes-3-Llama-3.1-8B-lorablated.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. + +