commit 485c243d052e3e881579754891f037ec779fb9b5 Author: ModelHub XC Date: Fri Jun 26 07:18:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Meta-Llama-3.1-8B-HerO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9468cdb --- /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 +Meta-Llama-3.1-8B-HerO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-HerO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-HerO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-HerO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-HerO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-HerO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-HerO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-HerO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-HerO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-HerO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-HerO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-HerO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-3.1-8B-HerO.IQ4_XS.gguf b/Meta-Llama-3.1-8B-HerO.IQ4_XS.gguf new file mode 100644 index 0000000..602eec0 --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b12cd1de0cdb33492c9734965f436ac5db4d341ff11ae3918d1d9c5e8e3bcde +size 4484367808 diff --git a/Meta-Llama-3.1-8B-HerO.Q2_K.gguf b/Meta-Llama-3.1-8B-HerO.Q2_K.gguf new file mode 100644 index 0000000..d117150 --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba47aea7327fa58aa381899f4c4f9ac58bdd2884f905d70cb3b22bb74f759b9 +size 3179136448 diff --git a/Meta-Llama-3.1-8B-HerO.Q3_K_L.gguf b/Meta-Llama-3.1-8B-HerO.Q3_K_L.gguf new file mode 100644 index 0000000..ead074f --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89a70ab112d65ce4a74540943f3087c9f38fbcf1daff1ff182dc7d64452af4d1 +size 4321961408 diff --git a/Meta-Llama-3.1-8B-HerO.Q3_K_M.gguf b/Meta-Llama-3.1-8B-HerO.Q3_K_M.gguf new file mode 100644 index 0000000..10de6bf --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef1e5459527182bcd4a8f4b232f7b0cec14bb938dccd9e312a9e539fb21a6ecc +size 4018922944 diff --git a/Meta-Llama-3.1-8B-HerO.Q3_K_S.gguf b/Meta-Llama-3.1-8B-HerO.Q3_K_S.gguf new file mode 100644 index 0000000..f3d43dc --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f530dba075f42e28fb76c759c2f1eff8d2f1dfee90be74999225f9633a30f1a +size 3664504256 diff --git a/Meta-Llama-3.1-8B-HerO.Q4_K_M.gguf b/Meta-Llama-3.1-8B-HerO.Q4_K_M.gguf new file mode 100644 index 0000000..74f2c0f --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:861e437fbcf74b88bc58747842fc9a0778010930ed9d34365915bade8a9f9378 +size 4920739264 diff --git a/Meta-Llama-3.1-8B-HerO.Q4_K_S.gguf b/Meta-Llama-3.1-8B-HerO.Q4_K_S.gguf new file mode 100644 index 0000000..b39cf0c --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21101033c1f000d8344b0b8f326c31a689a1aec1ef2b091205dc81d1edb9c024 +size 4692673984 diff --git a/Meta-Llama-3.1-8B-HerO.Q5_K_M.gguf b/Meta-Llama-3.1-8B-HerO.Q5_K_M.gguf new file mode 100644 index 0000000..a832e34 --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb67ae7145ef1e978a9bda27bb998ccf0655cbfb490703944f5d7e5bb8c7096 +size 5732992448 diff --git a/Meta-Llama-3.1-8B-HerO.Q5_K_S.gguf b/Meta-Llama-3.1-8B-HerO.Q5_K_S.gguf new file mode 100644 index 0000000..6bee93a --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:888a74710a20515195e31f864e5ae3177c955d6f13ebd95a8d95689eaf641c8d +size 5599299008 diff --git a/Meta-Llama-3.1-8B-HerO.Q6_K.gguf b/Meta-Llama-3.1-8B-HerO.Q6_K.gguf new file mode 100644 index 0000000..ae933ec --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c09e4ce46cb85522560597f67f4566bf1509535a0c919cc80167c683c21a544 +size 6596011456 diff --git a/Meta-Llama-3.1-8B-HerO.Q8_0.gguf b/Meta-Llama-3.1-8B-HerO.Q8_0.gguf new file mode 100644 index 0000000..a5a07ac --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f560cacf4f33a74aed62d083daae67fb38ffeb3cacd63f17c26f0f3dac559687 +size 8540775872 diff --git a/Meta-Llama-3.1-8B-HerO.f16.gguf b/Meta-Llama-3.1-8B-HerO.f16.gguf new file mode 100644 index 0000000..48e8537 --- /dev/null +++ b/Meta-Llama-3.1-8B-HerO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b030c38406435969ad435acb420e10d2be4337d2bf79dff2e4019dad9d333056 +size 16068896192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a214edf --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: humane-lab/Meta-Llama-3.1-8B-HerO +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/humane-lab/Meta-Llama-3.1-8B-HerO + + +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/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-HerO-GGUF/resolve/main/Meta-Llama-3.1-8B-HerO.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. + +