commit eff3bff0fe5d9a40c1bcc3f580b52510014bfb4c Author: ModelHub XC Date: Sat May 23 18:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ba7e044 --- /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-Breeze2-3B-Instruct-Text.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-3B-Instruct-Text.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-3B-Instruct-Text.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-3B-Instruct-Text.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-3B-Instruct-Text.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-3B-Instruct-Text.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-3B-Instruct-Text.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-3B-Instruct-Text.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-3B-Instruct-Text.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-3B-Instruct-Text.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-3B-Instruct-Text.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-3B-Instruct-Text.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Breeze2-3B-Instruct-Text.IQ4_XS.gguf b/Llama-Breeze2-3B-Instruct-Text.IQ4_XS.gguf new file mode 100644 index 0000000..2387ded --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39374541acda79576e36d6952044857d8eefa31915651fe35da6bc83bcdaccbd +size 2050220544 diff --git a/Llama-Breeze2-3B-Instruct-Text.Q2_K.gguf b/Llama-Breeze2-3B-Instruct-Text.Q2_K.gguf new file mode 100644 index 0000000..02a4649 --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96dd034c646b0ab2fbfa057d3e5c37af34a9dd6fe7b629ee612f0b351f03c79 +size 1493217792 diff --git a/Llama-Breeze2-3B-Instruct-Text.Q3_K_L.gguf b/Llama-Breeze2-3B-Instruct-Text.Q3_K_L.gguf new file mode 100644 index 0000000..62ce468 --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d92df23d8bd3bee2a6601a60d25524376873be1d9db945b9211209143004fb +size 1984645632 diff --git a/Llama-Breeze2-3B-Instruct-Text.Q3_K_M.gguf b/Llama-Breeze2-3B-Instruct-Text.Q3_K_M.gguf new file mode 100644 index 0000000..5b0c1aa --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de38f80758b63d1a9ae0d23e4ab8ecc129f04c1f9858aaf81993e495e4f2c9cb +size 1856457216 diff --git a/Llama-Breeze2-3B-Instruct-Text.Q3_K_S.gguf b/Llama-Breeze2-3B-Instruct-Text.Q3_K_S.gguf new file mode 100644 index 0000000..90814fe --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80bee770a51c27a771e1544ddaafff77c079b584b9590a888daf133760128fb6 +size 1712146944 diff --git a/Llama-Breeze2-3B-Instruct-Text.Q4_K_M.gguf b/Llama-Breeze2-3B-Instruct-Text.Q4_K_M.gguf new file mode 100644 index 0000000..49171fd --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6cc86eea1084ddc03b682f2c966a7a8fa8c03375178d2902c4e6cb560d073d4 +size 2241004032 diff --git a/Llama-Breeze2-3B-Instruct-Text.Q4_K_S.gguf b/Llama-Breeze2-3B-Instruct-Text.Q4_K_S.gguf new file mode 100644 index 0000000..8c56909 --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f260ee524dce9f7b358d8536b0f9cdc001fc3cf6ee959500416b05e481f59d0 +size 2149827072 diff --git a/Llama-Breeze2-3B-Instruct-Text.Q5_K_M.gguf b/Llama-Breeze2-3B-Instruct-Text.Q5_K_M.gguf new file mode 100644 index 0000000..a44886a --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8867347e60ab44a4f14ab79b7b3b89d268aa790d1c9c09e486e72150a23b58cc +size 2593030656 diff --git a/Llama-Breeze2-3B-Instruct-Text.Q5_K_S.gguf b/Llama-Breeze2-3B-Instruct-Text.Q5_K_S.gguf new file mode 100644 index 0000000..73fd33c --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bd021b6fad1af797899409a4aaf3f671416e6ca85e89b018a940199ce80b0dc +size 2540388864 diff --git a/Llama-Breeze2-3B-Instruct-Text.Q6_K.gguf b/Llama-Breeze2-3B-Instruct-Text.Q6_K.gguf new file mode 100644 index 0000000..eba0368 --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2663e2ad589b3632261005cea7f7e95730a82d79e9f620b33cb16b8e1eae8906 +size 2967058944 diff --git a/Llama-Breeze2-3B-Instruct-Text.Q8_0.gguf b/Llama-Breeze2-3B-Instruct-Text.Q8_0.gguf new file mode 100644 index 0000000..8b9e55f --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ca62383b851a1bf18ad2bb76ea3ecf74e2d0ee31e85f8dc1f525a2d8e0d7cb +size 3840526848 diff --git a/Llama-Breeze2-3B-Instruct-Text.f16.gguf b/Llama-Breeze2-3B-Instruct-Text.f16.gguf new file mode 100644 index 0000000..fc27505 --- /dev/null +++ b/Llama-Breeze2-3B-Instruct-Text.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77562f75efd2201606b6747617de82e6efd71074aeebc2991bf134a1c96bf8df +size 7221692928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3941a0e --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: PenutChen/Llama-Breeze2-3B-Instruct-Text +language: +- en +- zh +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/PenutChen/Llama-Breeze2-3B-Instruct-Text + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-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/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-3B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-3B-Instruct-Text.f16.gguf) | f16 | 7.3 | 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. + +