commit 4effdb88c3853796ac5c8e63785a821e11fef209 Author: ModelHub XC Date: Fri Oct 9 08:00:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Hermes-slerp-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f3869a9 --- /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-Hermes-slerp-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Hermes-slerp-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Hermes-slerp-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Hermes-slerp-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Hermes-slerp-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Hermes-slerp-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Hermes-slerp-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Hermes-slerp-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Hermes-slerp-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Hermes-slerp-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Hermes-slerp-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Hermes-slerp-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Hermes-slerp-8B.IQ4_XS.gguf b/Llama-Hermes-slerp-8B.IQ4_XS.gguf new file mode 100644 index 0000000..a17bd49 --- /dev/null +++ b/Llama-Hermes-slerp-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d763ad3ace2c9ae2dd3235875b517ee07daec40c960dc5aa42161fa7c4d6d7fe +size 4484368832 diff --git a/Llama-Hermes-slerp-8B.Q2_K.gguf b/Llama-Hermes-slerp-8B.Q2_K.gguf new file mode 100644 index 0000000..640f99a --- /dev/null +++ b/Llama-Hermes-slerp-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb181b6e828f2ef40235618639674d84bc7015743f92fba442f016b61e418874 +size 3179137472 diff --git a/Llama-Hermes-slerp-8B.Q3_K_L.gguf b/Llama-Hermes-slerp-8B.Q3_K_L.gguf new file mode 100644 index 0000000..c50d697 --- /dev/null +++ b/Llama-Hermes-slerp-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441dd92cb3faace8a348cefed7764490b7c6b70267a0b8c635ace1f7c4446532 +size 4321962432 diff --git a/Llama-Hermes-slerp-8B.Q3_K_M.gguf b/Llama-Hermes-slerp-8B.Q3_K_M.gguf new file mode 100644 index 0000000..222b556 --- /dev/null +++ b/Llama-Hermes-slerp-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f30d51e2669bcb8af5d01ab4258552d6cd4f031ea0158694d23607e31c3b0bb +size 4018923968 diff --git a/Llama-Hermes-slerp-8B.Q3_K_S.gguf b/Llama-Hermes-slerp-8B.Q3_K_S.gguf new file mode 100644 index 0000000..5ec5778 --- /dev/null +++ b/Llama-Hermes-slerp-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:749ff660619aaa1e9289707956a30e53040073dd8dbca76360e169e27a5e4fe9 +size 3664505280 diff --git a/Llama-Hermes-slerp-8B.Q4_K_M.gguf b/Llama-Hermes-slerp-8B.Q4_K_M.gguf new file mode 100644 index 0000000..097e47d --- /dev/null +++ b/Llama-Hermes-slerp-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec3918fabb049cb32e54be2a53df27fe46dd958c94b781b32c4fbcbecb18b3d7 +size 4920740288 diff --git a/Llama-Hermes-slerp-8B.Q4_K_S.gguf b/Llama-Hermes-slerp-8B.Q4_K_S.gguf new file mode 100644 index 0000000..693a083 --- /dev/null +++ b/Llama-Hermes-slerp-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0586ae56c3919d29a7a5c8733715985935856de0b3130b859ec91ee518f39d3 +size 4692675008 diff --git a/Llama-Hermes-slerp-8B.Q5_K_M.gguf b/Llama-Hermes-slerp-8B.Q5_K_M.gguf new file mode 100644 index 0000000..a32181b --- /dev/null +++ b/Llama-Hermes-slerp-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3cb003651322f0714db17fa4f531f1adb411d53065ba199575ed9e074ec67b4 +size 5732993472 diff --git a/Llama-Hermes-slerp-8B.Q5_K_S.gguf b/Llama-Hermes-slerp-8B.Q5_K_S.gguf new file mode 100644 index 0000000..b1f405a --- /dev/null +++ b/Llama-Hermes-slerp-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d08317df2d31216fe2024996a68cd731ce306dbf8cf8dfb9cdb0f03876f8f174 +size 5599300032 diff --git a/Llama-Hermes-slerp-8B.Q6_K.gguf b/Llama-Hermes-slerp-8B.Q6_K.gguf new file mode 100644 index 0000000..40dd67a --- /dev/null +++ b/Llama-Hermes-slerp-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9426e5a1456ef6ab7cc64404b552aba2d1b9df88f955cd222b1e67497ceff46 +size 6596012480 diff --git a/Llama-Hermes-slerp-8B.Q8_0.gguf b/Llama-Hermes-slerp-8B.Q8_0.gguf new file mode 100644 index 0000000..6de424a --- /dev/null +++ b/Llama-Hermes-slerp-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b0198e52aafeeb1bc577d7a9e4e998958ec8a0cec646dc187bda3f471db46d +size 8540776896 diff --git a/Llama-Hermes-slerp-8B.f16.gguf b/Llama-Hermes-slerp-8B.f16.gguf new file mode 100644 index 0000000..ade0deb --- /dev/null +++ b/Llama-Hermes-slerp-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:503be09e4c92f5469348f6aa45ad19c024affed0469f735bdfc12a0fdb260c6c +size 16068897216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..56124e9 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: hotmailuser/Llama-Hermes-slerp-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/hotmailuser/Llama-Hermes-slerp-8B + + +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-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Hermes-slerp-8B-GGUF/resolve/main/Llama-Hermes-slerp-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. + +