commit 58360c562a45d3691dc44d30bdfca929709336ca Author: ModelHub XC Date: Tue Jun 2 11:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Buzz-8b-Large-v0.5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e8871f3 --- /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 +Buzz-8b-Large-v0.5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Buzz-8b-Large-v0.5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Buzz-8b-Large-v0.5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Buzz-8b-Large-v0.5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Buzz-8b-Large-v0.5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Buzz-8b-Large-v0.5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Buzz-8b-Large-v0.5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Buzz-8b-Large-v0.5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Buzz-8b-Large-v0.5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Buzz-8b-Large-v0.5.f16.gguf filter=lfs diff=lfs merge=lfs -text +Buzz-8b-Large-v0.5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Buzz-8b-Large-v0.5.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Buzz-8b-Large-v0.5.IQ4_XS.gguf b/Buzz-8b-Large-v0.5.IQ4_XS.gguf new file mode 100644 index 0000000..600bce6 --- /dev/null +++ b/Buzz-8b-Large-v0.5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c5d136c26f81a0ccd27a66628938729e4ec413595d27d91b1bd425f5155eef9 +size 4484363552 diff --git a/Buzz-8b-Large-v0.5.Q2_K.gguf b/Buzz-8b-Large-v0.5.Q2_K.gguf new file mode 100644 index 0000000..c90756c --- /dev/null +++ b/Buzz-8b-Large-v0.5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:833c3de6040c828f14f4956b310b9ba6f7d0f28e092604784cd92e856a0bc50e +size 3179132192 diff --git a/Buzz-8b-Large-v0.5.Q3_K_L.gguf b/Buzz-8b-Large-v0.5.Q3_K_L.gguf new file mode 100644 index 0000000..33f02d1 --- /dev/null +++ b/Buzz-8b-Large-v0.5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a43a7f2889b8c0f3bfc3b87024934cb9c702e51731dbeee25329b69c412b7baa +size 4321957152 diff --git a/Buzz-8b-Large-v0.5.Q3_K_M.gguf b/Buzz-8b-Large-v0.5.Q3_K_M.gguf new file mode 100644 index 0000000..7811f37 --- /dev/null +++ b/Buzz-8b-Large-v0.5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3c97c8ff326e7368bb5725df3825d5e46fed92054721edfddeacb76096e6380 +size 4018918688 diff --git a/Buzz-8b-Large-v0.5.Q3_K_S.gguf b/Buzz-8b-Large-v0.5.Q3_K_S.gguf new file mode 100644 index 0000000..ff805e2 --- /dev/null +++ b/Buzz-8b-Large-v0.5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c43cb3333fafcd7e211e9846f17502207c97d73927f308303ebe056274c0410a +size 3664500000 diff --git a/Buzz-8b-Large-v0.5.Q4_0_4_4.gguf b/Buzz-8b-Large-v0.5.Q4_0_4_4.gguf new file mode 100644 index 0000000..4dd5b68 --- /dev/null +++ b/Buzz-8b-Large-v0.5.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2662f2f039a5aeaf94cde7270cb68567ac24300a90510fa0dc2b6fe9537321d7 +size 4661212448 diff --git a/Buzz-8b-Large-v0.5.Q4_K_M.gguf b/Buzz-8b-Large-v0.5.Q4_K_M.gguf new file mode 100644 index 0000000..99a00e2 --- /dev/null +++ b/Buzz-8b-Large-v0.5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0eac0fd176e20ff53575bf706a2fe761ab764b7e1ea7690afb3d14ec5ba0b6d +size 4920735008 diff --git a/Buzz-8b-Large-v0.5.Q4_K_S.gguf b/Buzz-8b-Large-v0.5.Q4_K_S.gguf new file mode 100644 index 0000000..b175b96 --- /dev/null +++ b/Buzz-8b-Large-v0.5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93c124ac503b2750053c9721e0583dd18644587ea7a04cbde4b52c3615cfaf8a +size 4692669728 diff --git a/Buzz-8b-Large-v0.5.Q5_K_M.gguf b/Buzz-8b-Large-v0.5.Q5_K_M.gguf new file mode 100644 index 0000000..624d07c --- /dev/null +++ b/Buzz-8b-Large-v0.5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db091650d775a2b175189e8ce195e5962a7a4f5d86c92a795e2f617b738e2557 +size 5732988192 diff --git a/Buzz-8b-Large-v0.5.Q5_K_S.gguf b/Buzz-8b-Large-v0.5.Q5_K_S.gguf new file mode 100644 index 0000000..219ef28 --- /dev/null +++ b/Buzz-8b-Large-v0.5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8198144386b85cd5547042ec47ba0ab7ef5ffd1b3d96c071f7341cb92d18f4c +size 5599294752 diff --git a/Buzz-8b-Large-v0.5.Q6_K.gguf b/Buzz-8b-Large-v0.5.Q6_K.gguf new file mode 100644 index 0000000..2de3d76 --- /dev/null +++ b/Buzz-8b-Large-v0.5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e481e9773fdc34a8c78d9356afb78fa490a7b27f69f689a826f7d9000478c1cd +size 6596007200 diff --git a/Buzz-8b-Large-v0.5.Q8_0.gguf b/Buzz-8b-Large-v0.5.Q8_0.gguf new file mode 100644 index 0000000..b2ceaac --- /dev/null +++ b/Buzz-8b-Large-v0.5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ce2081f0f369ee15917abbec20cc68844ef386a1aa2aa2001aa4808e2861ee2 +size 8540771616 diff --git a/Buzz-8b-Large-v0.5.f16.gguf b/Buzz-8b-Large-v0.5.f16.gguf new file mode 100644 index 0000000..c69ae0e --- /dev/null +++ b/Buzz-8b-Large-v0.5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a2af72034f9b3a69d9527733c4a0e08cdc11692443220a50bf717951a000cb8 +size 16068891936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aee93cc --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: H-D-T/Buzz-8b-Large-v0.5 +datasets: +- H-D-T/Buzz +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- axolotl +- Alignment-Lab-AI +- Meta-Llama-3 +--- +## About + + + + + + +static quants of https://huggingface.co/H-D-T/Buzz-8b-Large-v0.5 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-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/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Buzz-8b-Large-v0.5-GGUF/resolve/main/Buzz-8b-Large-v0.5.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. + +