commit f96e199e503123385dd5b1c5d752b25b5d7cbc62 Author: ModelHub XC Date: Sat Jun 13 14:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-NuminaQA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a580f7a --- /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-3.2-3B-NuminaQA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-NuminaQA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-NuminaQA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-NuminaQA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-NuminaQA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-NuminaQA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-NuminaQA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-NuminaQA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-NuminaQA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-NuminaQA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-NuminaQA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-NuminaQA.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-NuminaQA.IQ4_XS.gguf b/Llama-3.2-3B-NuminaQA.IQ4_XS.gguf new file mode 100644 index 0000000..77ceb06 --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d8790a7762c818407dd8806e7f5ee6b07bbea92db19fe303264a95530937c8 +size 1840903424 diff --git a/Llama-3.2-3B-NuminaQA.Q2_K.gguf b/Llama-3.2-3B-NuminaQA.Q2_K.gguf new file mode 100644 index 0000000..3bd28c9 --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:221bd39ba08ed8f050619c18368d40fe9164ec57bf4d994bf9c4d1ee1a73fc97 +size 1363932416 diff --git a/Llama-3.2-3B-NuminaQA.Q3_K_L.gguf b/Llama-3.2-3B-NuminaQA.Q3_K_L.gguf new file mode 100644 index 0000000..8c7691d --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a26af27e4009d7171152560a603e496ebdf7d60d273316429bdadc22955418c +size 1815344384 diff --git a/Llama-3.2-3B-NuminaQA.Q3_K_M.gguf b/Llama-3.2-3B-NuminaQA.Q3_K_M.gguf new file mode 100644 index 0000000..298ad1a --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92d1b7c70f8b3f6e6f9163b6a7a09f759b3b82a9b513f7fc30515231d9d1904c +size 1687155968 diff --git a/Llama-3.2-3B-NuminaQA.Q3_K_S.gguf b/Llama-3.2-3B-NuminaQA.Q3_K_S.gguf new file mode 100644 index 0000000..d8b05b1 --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84b20febdcab375b465bb34b7090c62384e034fcc199b2c6711351cec776d711 +size 1542845696 diff --git a/Llama-3.2-3B-NuminaQA.Q4_K_M.gguf b/Llama-3.2-3B-NuminaQA.Q4_K_M.gguf new file mode 100644 index 0000000..36b6ff3 --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e938b4b2fc2182cfb9751203b0709e00d769ac957cb4ad9d1390d8b5caba7e4 +size 2019374336 diff --git a/Llama-3.2-3B-NuminaQA.Q4_K_S.gguf b/Llama-3.2-3B-NuminaQA.Q4_K_S.gguf new file mode 100644 index 0000000..b19cf98 --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54568dfe34bd2fc2b3737f27f9845b41aa84e42a8a935b99a8cedfb10f646863 +size 1928197376 diff --git a/Llama-3.2-3B-NuminaQA.Q5_K_M.gguf b/Llama-3.2-3B-NuminaQA.Q5_K_M.gguf new file mode 100644 index 0000000..85b70b2 --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a78e7546a226fa4ce0663c47041c53934b4d520fde69b4ce283fb9a433acff6d +size 2322150656 diff --git a/Llama-3.2-3B-NuminaQA.Q5_K_S.gguf b/Llama-3.2-3B-NuminaQA.Q5_K_S.gguf new file mode 100644 index 0000000..f0af3c8 --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26ed31d9643c792884da701a62b0c3016d8f75faddd0b77010d8da02334b0266 +size 2269508864 diff --git a/Llama-3.2-3B-NuminaQA.Q6_K.gguf b/Llama-3.2-3B-NuminaQA.Q6_K.gguf new file mode 100644 index 0000000..26cd16d --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa0b0a22e679b64161c8e552d1c384e28275f8384788df5fd7ff0c6f4e0c1a58 +size 2643850496 diff --git a/Llama-3.2-3B-NuminaQA.Q8_0.gguf b/Llama-3.2-3B-NuminaQA.Q8_0.gguf new file mode 100644 index 0000000..64ebe6d --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff91555493c81558727576aafa3bc1a94482aa80e1a3b50072ed0055a3509318 +size 3421895936 diff --git a/Llama-3.2-3B-NuminaQA.f16.gguf b/Llama-3.2-3B-NuminaQA.f16.gguf new file mode 100644 index 0000000..c91c0e7 --- /dev/null +++ b/Llama-3.2-3B-NuminaQA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:854ccc401e45b94164834e604185ff7bcd10b954a3c63e6020f40be3b7e2e720 +size 6433684736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ef563fc --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: lkevinzc/Llama-3.2-3B-NuminaQA +datasets: +- lkevinzc/numia-1.5-qa-concatenated +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/lkevinzc/Llama-3.2-3B-NuminaQA + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-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-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-NuminaQA-GGUF/resolve/main/Llama-3.2-3B-NuminaQA.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. + +