commit 0be07a78b84cb568009849973270814dd1126975 Author: ModelHub XC Date: Thu Oct 22 01:10:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/sonnet-llama-3.2-3b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e8c190b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +sonnet-llama-3.2-3b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +sonnet-llama-3.2-3b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sonnet-llama-3.2-3b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sonnet-llama-3.2-3b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sonnet-llama-3.2-3b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +sonnet-llama-3.2-3b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +sonnet-llama-3.2-3b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sonnet-llama-3.2-3b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sonnet-llama-3.2-3b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sonnet-llama-3.2-3b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +sonnet-llama-3.2-3b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b7cea4c --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: legionlm/sonnet-llama-3.2-3b +datasets: +- jeffmeloy/sonnet3.5_science_conversations +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/legionlm/sonnet-llama-3.2-3b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#sonnet-llama-3.2-3b-GGUF).*** + +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/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/sonnet-llama-3.2-3b-GGUF/resolve/main/sonnet-llama-3.2-3b.f16.gguf) | f16 | 6.5 | 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. + + diff --git a/sonnet-llama-3.2-3b.IQ4_XS.gguf b/sonnet-llama-3.2-3b.IQ4_XS.gguf new file mode 100644 index 0000000..5bf8e4d --- /dev/null +++ b/sonnet-llama-3.2-3b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e41c981e62bb5a21b871d27c7bdaddc96861f3654a341bdba2e7ec97fb1a2b9d +size 1840908064 diff --git a/sonnet-llama-3.2-3b.Q2_K.gguf b/sonnet-llama-3.2-3b.Q2_K.gguf new file mode 100644 index 0000000..e7e5c35 --- /dev/null +++ b/sonnet-llama-3.2-3b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53dd9622ead78f992f64319462239661a5f63dec235ac9297d18175b42dc60cd +size 1363937056 diff --git a/sonnet-llama-3.2-3b.Q3_K_L.gguf b/sonnet-llama-3.2-3b.Q3_K_L.gguf new file mode 100644 index 0000000..7fd071c --- /dev/null +++ b/sonnet-llama-3.2-3b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ad7cb61832cf748e291ed0932c2e271e949f021c14c858222e70426b359bd6 +size 1815349024 diff --git a/sonnet-llama-3.2-3b.Q3_K_M.gguf b/sonnet-llama-3.2-3b.Q3_K_M.gguf new file mode 100644 index 0000000..1b2d9f3 --- /dev/null +++ b/sonnet-llama-3.2-3b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95f7e435d6b1006035b7f4efbf89cb3d457bf0035f6c100147409c7503690a84 +size 1687160608 diff --git a/sonnet-llama-3.2-3b.Q3_K_S.gguf b/sonnet-llama-3.2-3b.Q3_K_S.gguf new file mode 100644 index 0000000..8b3ed29 --- /dev/null +++ b/sonnet-llama-3.2-3b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1483719a3f1ad5357bad6644d7116e6ff2a9f37f69d9c4106a3c0042c72ebb90 +size 1542850336 diff --git a/sonnet-llama-3.2-3b.Q4_K_M.gguf b/sonnet-llama-3.2-3b.Q4_K_M.gguf new file mode 100644 index 0000000..cf66663 --- /dev/null +++ b/sonnet-llama-3.2-3b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14b11becd26bc88faa0d9e75c413c68efc069e39fe692a67fc2da1d7909c9c9 +size 2019378976 diff --git a/sonnet-llama-3.2-3b.Q4_K_S.gguf b/sonnet-llama-3.2-3b.Q4_K_S.gguf new file mode 100644 index 0000000..0f97d75 --- /dev/null +++ b/sonnet-llama-3.2-3b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:311736edaf95a7316f3482580e1f47e34fe31ba1f31ee4052a25ef4b1e3dbcfe +size 1928202016 diff --git a/sonnet-llama-3.2-3b.Q5_K_M.gguf b/sonnet-llama-3.2-3b.Q5_K_M.gguf new file mode 100644 index 0000000..7f6856d --- /dev/null +++ b/sonnet-llama-3.2-3b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:464fcd069e9924872780504f13427ac3f0e93df6202831d3248b910a2d1f387c +size 2322155296 diff --git a/sonnet-llama-3.2-3b.Q5_K_S.gguf b/sonnet-llama-3.2-3b.Q5_K_S.gguf new file mode 100644 index 0000000..fc5eb9d --- /dev/null +++ b/sonnet-llama-3.2-3b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18501668a0d8fbe3e0194d3a5e2aea8b7cccf3a5ee7f91fd9658abcd2d80e589 +size 2269513504 diff --git a/sonnet-llama-3.2-3b.Q6_K.gguf b/sonnet-llama-3.2-3b.Q6_K.gguf new file mode 100644 index 0000000..e2b3864 --- /dev/null +++ b/sonnet-llama-3.2-3b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7f55ab730643f6142342c68ad82828ece5b99733e5e9073be1999debc7812d8 +size 2643855136 diff --git a/sonnet-llama-3.2-3b.Q8_0.gguf b/sonnet-llama-3.2-3b.Q8_0.gguf new file mode 100644 index 0000000..56f7504 --- /dev/null +++ b/sonnet-llama-3.2-3b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9acdb3f764b8f1a2c241be7a6c6095ef7cf4d066fc5309b4f09e28805cc99112 +size 3421900576 diff --git a/sonnet-llama-3.2-3b.f16.gguf b/sonnet-llama-3.2-3b.f16.gguf new file mode 100644 index 0000000..b1219f1 --- /dev/null +++ b/sonnet-llama-3.2-3b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f256a2b65c83032e800a6fda4c8066627d302b3752b4c21a716fd068d7ac6842 +size 6433689376