commit a1f19a603ed9ea4be2285d734a714d512d2b4a55 Author: ModelHub XC Date: Sun May 24 15:06:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f5a4e24 --- /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-Breeze2-8B-Instruct-Text.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-8B-Instruct-Text.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-8B-Instruct-Text.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-8B-Instruct-Text.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-8B-Instruct-Text.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-8B-Instruct-Text.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-8B-Instruct-Text.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-8B-Instruct-Text.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-8B-Instruct-Text.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-8B-Instruct-Text.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-8B-Instruct-Text.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Breeze2-8B-Instruct-Text.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Breeze2-8B-Instruct-Text.IQ4_XS.gguf b/Llama-Breeze2-8B-Instruct-Text.IQ4_XS.gguf new file mode 100644 index 0000000..d425200 --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:631eaca3009e2f624b518077f864004a54061b5fa6f9ef2df3607c34d9237aab +size 4484366944 diff --git a/Llama-Breeze2-8B-Instruct-Text.Q2_K.gguf b/Llama-Breeze2-8B-Instruct-Text.Q2_K.gguf new file mode 100644 index 0000000..e094b77 --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85c2975f6a96301767b23b918c4b18a5ed44726aca4353928b4c6cfde767df9f +size 3179135584 diff --git a/Llama-Breeze2-8B-Instruct-Text.Q3_K_L.gguf b/Llama-Breeze2-8B-Instruct-Text.Q3_K_L.gguf new file mode 100644 index 0000000..52f1143 --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19cc35a068c054e81708ad8d4482fa2e6d4d53e49ad2153a054d3ce44172206f +size 4321960544 diff --git a/Llama-Breeze2-8B-Instruct-Text.Q3_K_M.gguf b/Llama-Breeze2-8B-Instruct-Text.Q3_K_M.gguf new file mode 100644 index 0000000..1b8e228 --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f170d8302af83f0fba376db44ac3b906940ee116ad0f65cfa669f120f7b4daac +size 4018922080 diff --git a/Llama-Breeze2-8B-Instruct-Text.Q3_K_S.gguf b/Llama-Breeze2-8B-Instruct-Text.Q3_K_S.gguf new file mode 100644 index 0000000..94ee829 --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc157c447475bd5e9165e8497456ab58d3f60e4086a18627c46829cb195a2e9 +size 3664503392 diff --git a/Llama-Breeze2-8B-Instruct-Text.Q4_K_M.gguf b/Llama-Breeze2-8B-Instruct-Text.Q4_K_M.gguf new file mode 100644 index 0000000..18b62dc --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece315ab938561438b37e6ad052e87328bc76a34b6457481e104b4ae1be8a150 +size 4920738400 diff --git a/Llama-Breeze2-8B-Instruct-Text.Q4_K_S.gguf b/Llama-Breeze2-8B-Instruct-Text.Q4_K_S.gguf new file mode 100644 index 0000000..ac0e1d5 --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18631ab8e20345e679410c8f6020f75b54035f413649c53de478e9e5b3070b06 +size 4692673120 diff --git a/Llama-Breeze2-8B-Instruct-Text.Q5_K_M.gguf b/Llama-Breeze2-8B-Instruct-Text.Q5_K_M.gguf new file mode 100644 index 0000000..705f670 --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73b06c547e607353048307dc91b52d39cac5ff37376168101220241f4360cad0 +size 5732991584 diff --git a/Llama-Breeze2-8B-Instruct-Text.Q5_K_S.gguf b/Llama-Breeze2-8B-Instruct-Text.Q5_K_S.gguf new file mode 100644 index 0000000..450b5c6 --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e70dffcc9d2822825752b250b4317f4d33a36e26381ee8084e97888b8464007 +size 5599298144 diff --git a/Llama-Breeze2-8B-Instruct-Text.Q6_K.gguf b/Llama-Breeze2-8B-Instruct-Text.Q6_K.gguf new file mode 100644 index 0000000..4e9c8e0 --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d93cf44129f801794261a68cdf3b6034f49cc6c798bcd6d8e3198fcae3bdae73 +size 6596010592 diff --git a/Llama-Breeze2-8B-Instruct-Text.Q8_0.gguf b/Llama-Breeze2-8B-Instruct-Text.Q8_0.gguf new file mode 100644 index 0000000..e1cb588 --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1400f90939baa98060d5ee35bc325326aa771e38fc74e93a7a3d85b8d036f211 +size 8540775008 diff --git a/Llama-Breeze2-8B-Instruct-Text.f16.gguf b/Llama-Breeze2-8B-Instruct-Text.f16.gguf new file mode 100644 index 0000000..e02da45 --- /dev/null +++ b/Llama-Breeze2-8B-Instruct-Text.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b65796b97c66248a59bcba360cda2466a8f543ff645616e1301f510376ca5e12 +size 16068895328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6f448f4 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: PenutChen/Llama-Breeze2-8B-Instruct-Text +language: +- en +- zh +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/PenutChen/Llama-Breeze2-8B-Instruct-Text + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-Breeze2-8B-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-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-GGUF/resolve/main/Llama-Breeze2-8B-Instruct-Text.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. + +