commit dd53f93808610670378c83b8e50dd83fe7b141b9 Author: ModelHub XC Date: Wed Apr 22 00:24:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6c31763 --- /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 +FuseChat-Llama-3.2-1B-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FuseChat-Llama-3.2-1B-SFT.IQ4_XS.gguf b/FuseChat-Llama-3.2-1B-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..ade4d46 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:847cd35601373e3ddf2e9e24b4dce42bdd24fa8af58a070d355c6c89137072a6 +size 748381120 diff --git a/FuseChat-Llama-3.2-1B-SFT.Q2_K.gguf b/FuseChat-Llama-3.2-1B-SFT.Q2_K.gguf new file mode 100644 index 0000000..e9604c5 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c78e8881ed302c5d0619d8f5e3dfeb693a1ce9e3b8e5e9618a793e6ea3177b87 +size 580871104 diff --git a/FuseChat-Llama-3.2-1B-SFT.Q3_K_L.gguf b/FuseChat-Llama-3.2-1B-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..f729a91 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b5eade01fdb354efa046eb8068671acda0272f99d09d9839fc06e5ce86450f +size 732521408 diff --git a/FuseChat-Llama-3.2-1B-SFT.Q3_K_M.gguf b/FuseChat-Llama-3.2-1B-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..cf1efca --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fd6da04ebc0d57e48e9fc654c030123255ea2563de61bc3e46ca1015af3cb58 +size 690840512 diff --git a/FuseChat-Llama-3.2-1B-SFT.Q3_K_S.gguf b/FuseChat-Llama-3.2-1B-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..f29a93d --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d7d9fcfad1ed9777e9db1f54c05c2291e9f6e1959b79a8fb7512296dd776f4 +size 641688512 diff --git a/FuseChat-Llama-3.2-1B-SFT.Q4_K_M.gguf b/FuseChat-Llama-3.2-1B-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..3a44e6c --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f459dd51ba7a305c14fc2c3490d052951e686841de20bf68dad4890363c1f2 +size 807691200 diff --git a/FuseChat-Llama-3.2-1B-SFT.Q4_K_S.gguf b/FuseChat-Llama-3.2-1B-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..6b132ed --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c008dfd3221c19f8f8d8dae6adf0962d6ea65f39b43d4140c97d4d8451d48be5 +size 775644096 diff --git a/FuseChat-Llama-3.2-1B-SFT.Q5_K_M.gguf b/FuseChat-Llama-3.2-1B-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..853b891 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:380a3b7b1a1c698a9c85c027c0c0cefbc6aa97d477bba78b7c8e3c5998c2606a +size 911500224 diff --git a/FuseChat-Llama-3.2-1B-SFT.Q5_K_S.gguf b/FuseChat-Llama-3.2-1B-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..41257d6 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a969671a83473457c75359c05860e9546b1e520329a4e7e1cd7573f2f5843e5 +size 892560320 diff --git a/FuseChat-Llama-3.2-1B-SFT.Q6_K.gguf b/FuseChat-Llama-3.2-1B-SFT.Q6_K.gguf new file mode 100644 index 0000000..2b9dfa1 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db4577dfc34c4ad99cd6cc2b2c21129565abc5c65661a109873d9ec826113b61 +size 1021797312 diff --git a/FuseChat-Llama-3.2-1B-SFT.Q8_0.gguf b/FuseChat-Llama-3.2-1B-SFT.Q8_0.gguf new file mode 100644 index 0000000..59c6545 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a634a37bf8b4b5a2b9d6348740d5f8a21faeca28686981d4ca73bbd89f80402 +size 1321079744 diff --git a/FuseChat-Llama-3.2-1B-SFT.f16.gguf b/FuseChat-Llama-3.2-1B-SFT.f16.gguf new file mode 100644 index 0000000..18e46d0 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec042805b5cd63280d53fe8f05aec63b28b5eb184d4636941d5cb21152071678 +size 2479592384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8e87b06 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: FuseAI/FuseChat-Llama-3.2-1B-SFT +datasets: +- FuseAI/FuseChat-3.0-SFT-Data +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/FuseAI/FuseChat-Llama-3.2-1B-SFT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-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/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-SFT-GGUF/resolve/main/FuseChat-Llama-3.2-1B-SFT.f16.gguf) | f16 | 2.6 | 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. + +