commit 6507f4d600f45204ec520f44665248090e18a385 Author: ModelHub XC Date: Tue Jun 16 08:44:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-Hermes8B-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bc2ab01 --- /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 +Qwen3-Hermes8B-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Hermes8B-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Hermes8B-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Hermes8B-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Hermes8B-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Hermes8B-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Hermes8B-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Hermes8B-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Hermes8B-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Hermes8B-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Hermes8B-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Hermes8B-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-Hermes8B-v1.IQ4_XS.gguf b/Qwen3-Hermes8B-v1.IQ4_XS.gguf new file mode 100644 index 0000000..654fc57 --- /dev/null +++ b/Qwen3-Hermes8B-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6e1d5b34492ccb80ca7f607b79291a77bfbeb3dfaf0990b49b02bf6b0a8107 +size 4593297408 diff --git a/Qwen3-Hermes8B-v1.Q2_K.gguf b/Qwen3-Hermes8B-v1.Q2_K.gguf new file mode 100644 index 0000000..914a171 --- /dev/null +++ b/Qwen3-Hermes8B-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee0212c61c78ae102512befa111e3e3000100db2dd5822034ad06d7e6999eefb +size 3281733632 diff --git a/Qwen3-Hermes8B-v1.Q3_K_L.gguf b/Qwen3-Hermes8B-v1.Q3_K_L.gguf new file mode 100644 index 0000000..1017bda --- /dev/null +++ b/Qwen3-Hermes8B-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a905e03c9e67babb563d7fb00d70904b7096e1fd2977198e2c68c1f85755f717 +size 4431394816 diff --git a/Qwen3-Hermes8B-v1.Q3_K_M.gguf b/Qwen3-Hermes8B-v1.Q3_K_M.gguf new file mode 100644 index 0000000..0c63744 --- /dev/null +++ b/Qwen3-Hermes8B-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb71c78716d074f61a977a300752e63fbead9f2e5e9face6cf22103657239c83 +size 4124162048 diff --git a/Qwen3-Hermes8B-v1.Q3_K_S.gguf b/Qwen3-Hermes8B-v1.Q3_K_S.gguf new file mode 100644 index 0000000..71991d2 --- /dev/null +++ b/Qwen3-Hermes8B-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08fffdbee79b80a37c935035ae23bda028995f8630770cffbc3415992b557f66 +size 3769612288 diff --git a/Qwen3-Hermes8B-v1.Q4_K_M.gguf b/Qwen3-Hermes8B-v1.Q4_K_M.gguf new file mode 100644 index 0000000..4b6bde4 --- /dev/null +++ b/Qwen3-Hermes8B-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cfe97d96b1add2103e2bf2599d61e4acd97ef34a467e4da03d1e12b3f771d8a +size 5027784704 diff --git a/Qwen3-Hermes8B-v1.Q4_K_S.gguf b/Qwen3-Hermes8B-v1.Q4_K_S.gguf new file mode 100644 index 0000000..4f1863f --- /dev/null +++ b/Qwen3-Hermes8B-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a02db405e058b62ce7af20c37c518ededba9c574e7472bc937c02d80a14dbad +size 4802013184 diff --git a/Qwen3-Hermes8B-v1.Q5_K_M.gguf b/Qwen3-Hermes8B-v1.Q5_K_M.gguf new file mode 100644 index 0000000..379f360 --- /dev/null +++ b/Qwen3-Hermes8B-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4867119e093678b94086f982aae9c0f78daf9c186d7b6303c96138083714aaf +size 5851113472 diff --git a/Qwen3-Hermes8B-v1.Q5_K_S.gguf b/Qwen3-Hermes8B-v1.Q5_K_S.gguf new file mode 100644 index 0000000..ed5105a --- /dev/null +++ b/Qwen3-Hermes8B-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59999d581361b966bfac0024b77457e73a40a01181306a352e6b6d6cde731b6c +size 5720762368 diff --git a/Qwen3-Hermes8B-v1.Q6_K.gguf b/Qwen3-Hermes8B-v1.Q6_K.gguf new file mode 100644 index 0000000..45734ae --- /dev/null +++ b/Qwen3-Hermes8B-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea97b0074a9f6fb5edeb17cec305a3934dc1c42d53cf7eeb3ea2faf3930d33e4 +size 6725900288 diff --git a/Qwen3-Hermes8B-v1.Q8_0.gguf b/Qwen3-Hermes8B-v1.Q8_0.gguf new file mode 100644 index 0000000..c2c0b25 --- /dev/null +++ b/Qwen3-Hermes8B-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7f2ec5a183cf1e3f8bd7b96580caa94dfa3b2eea87cfc78b1366d77f39ccea +size 8709519360 diff --git a/Qwen3-Hermes8B-v1.f16.gguf b/Qwen3-Hermes8B-v1.f16.gguf new file mode 100644 index 0000000..4603bb9 --- /dev/null +++ b/Qwen3-Hermes8B-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:babe5bd0076657f9a83e20b5b35c7a97428d388d1f3381fbf2ae49711b757f4c +size 16388044800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3d355bd --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: justinj92/Qwen3-Hermes8B-v1 +datasets: +- NousResearch/Hermes-3-Dataset +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- axolotl +- reasoning +- math +- commonsense +--- +## About + + + + + + +static quants of https://huggingface.co/justinj92/Qwen3-Hermes8B-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Hermes8B-v1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-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/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Hermes8B-v1-GGUF/resolve/main/Qwen3-Hermes8B-v1.f16.gguf) | f16 | 16.5 | 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. + +