commit 1566afb1172f43ffe654c3097af66e5bfb63a0bf Author: ModelHub XC Date: Tue Sep 29 11:09:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ed8fa4f --- /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-3.2-1B-SFT-MW.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.2-1B-SFT-MW.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.2-1B-SFT-MW.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.2-1B-SFT-MW.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.2-1B-SFT-MW.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.2-1B-SFT-MW.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.2-1B-SFT-MW.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.2-1B-SFT-MW.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.2-1B-SFT-MW.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.2-1B-SFT-MW.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.2-1B-SFT-MW.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.2-1B-SFT-MW.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMA-3.2-1B-SFT-MW.IQ4_XS.gguf b/LLaMA-3.2-1B-SFT-MW.IQ4_XS.gguf new file mode 100644 index 0000000..572f5a3 --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc4a5a5d19899dc0ee9a3cabbb77bae631958c1e6489e33336a32d82cbc0b8e8 +size 748381216 diff --git a/LLaMA-3.2-1B-SFT-MW.Q2_K.gguf b/LLaMA-3.2-1B-SFT-MW.Q2_K.gguf new file mode 100644 index 0000000..b183ccd --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7136575cc876a0070193c31e969519c3b1d9ad34d52bf224d26992f088e3f2c7 +size 580871200 diff --git a/LLaMA-3.2-1B-SFT-MW.Q3_K_L.gguf b/LLaMA-3.2-1B-SFT-MW.Q3_K_L.gguf new file mode 100644 index 0000000..ea4d00a --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3d7eb5a431d883cfaf4616642e3160e89143c6f13a3c816f059d6742e5f7d66 +size 732521504 diff --git a/LLaMA-3.2-1B-SFT-MW.Q3_K_M.gguf b/LLaMA-3.2-1B-SFT-MW.Q3_K_M.gguf new file mode 100644 index 0000000..89cb4ae --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10ff550a0fc2bc7f14b5c0b52d39f9a6888e476d89c40611d08dbec56ce9672d +size 690840608 diff --git a/LLaMA-3.2-1B-SFT-MW.Q3_K_S.gguf b/LLaMA-3.2-1B-SFT-MW.Q3_K_S.gguf new file mode 100644 index 0000000..0022a3c --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9091fc43c64905eed8a8f60dea21347434748420bb404b9d1b9e69cd90524fb4 +size 641688608 diff --git a/LLaMA-3.2-1B-SFT-MW.Q4_K_M.gguf b/LLaMA-3.2-1B-SFT-MW.Q4_K_M.gguf new file mode 100644 index 0000000..22689a0 --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e2dc54a92f77fa81d57e730d08c10dad179e5531499c33da21b584ae8e3eab +size 807691296 diff --git a/LLaMA-3.2-1B-SFT-MW.Q4_K_S.gguf b/LLaMA-3.2-1B-SFT-MW.Q4_K_S.gguf new file mode 100644 index 0000000..708215f --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85d5439702b682e2de37632e888552cf92f2dd5c7e941695a5e16ac573045c0 +size 775644192 diff --git a/LLaMA-3.2-1B-SFT-MW.Q5_K_M.gguf b/LLaMA-3.2-1B-SFT-MW.Q5_K_M.gguf new file mode 100644 index 0000000..8a2be3e --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b85580cacb084c2b27a1816b78ecda3fc0c75ab63a8de7e2ebd5a19b6039c64 +size 911500320 diff --git a/LLaMA-3.2-1B-SFT-MW.Q5_K_S.gguf b/LLaMA-3.2-1B-SFT-MW.Q5_K_S.gguf new file mode 100644 index 0000000..50fe723 --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d533d668b3ded3eea1068891ffadb2bf6db6473bac3e5f0672ded03a749d25 +size 892560416 diff --git a/LLaMA-3.2-1B-SFT-MW.Q6_K.gguf b/LLaMA-3.2-1B-SFT-MW.Q6_K.gguf new file mode 100644 index 0000000..593bdf9 --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42790f3427fb6298c1abb6ed0e4ba0cd770f2451deac8c8ecb08b3c9dc2fd0c0 +size 1021797408 diff --git a/LLaMA-3.2-1B-SFT-MW.Q8_0.gguf b/LLaMA-3.2-1B-SFT-MW.Q8_0.gguf new file mode 100644 index 0000000..de60e60 --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a41d61bef5ec105075d58f8b8642be8350829ed3d14b42243a3472257d9fa6d3 +size 1321079840 diff --git a/LLaMA-3.2-1B-SFT-MW.f16.gguf b/LLaMA-3.2-1B-SFT-MW.f16.gguf new file mode 100644 index 0000000..50ca18f --- /dev/null +++ b/LLaMA-3.2-1B-SFT-MW.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2a5e423513dfac97885a66fc33add55371e493f3be5628527756096ea589bf3 +size 2479592480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5784fc8 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Norquinal/LLaMA-3.2-1B-SFT-MW +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Norquinal/LLaMA-3.2-1B-SFT-MW + + +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/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.2-1B-SFT-MW-GGUF/resolve/main/LLaMA-3.2-1B-SFT-MW.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. + +