commit 288f99b7336bc18a5c71d56043d9d507a6484b1a Author: ModelHub XC Date: Mon Sep 7 08:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Creative-Lora-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..74a4c48 --- /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-Creative-Lora.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Creative-Lora.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Creative-Lora.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Creative-Lora.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Creative-Lora.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Creative-Lora.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Creative-Lora.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Creative-Lora.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Creative-Lora.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Creative-Lora.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Creative-Lora.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Creative-Lora.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Creative-Lora.IQ4_XS.gguf b/Llama-3.2-1B-Creative-Lora.IQ4_XS.gguf new file mode 100644 index 0000000..134f53a --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:496b57a902e0a4b46b11f11838ae973f4b4d9069a42a05ec5951c761c0401dfb +size 748381056 diff --git a/Llama-3.2-1B-Creative-Lora.Q2_K.gguf b/Llama-3.2-1B-Creative-Lora.Q2_K.gguf new file mode 100644 index 0000000..bf002a1 --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50f7ac977bb9bd4d9d7a997d57d7dda02fa80c2b7db086b8d1f5ba5c588725d +size 580871040 diff --git a/Llama-3.2-1B-Creative-Lora.Q3_K_L.gguf b/Llama-3.2-1B-Creative-Lora.Q3_K_L.gguf new file mode 100644 index 0000000..fd0cc96 --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e811f4389d1467fe28c1447ac9d2523beba1603343af5cc8f9f9f4f7beafb3c9 +size 732521344 diff --git a/Llama-3.2-1B-Creative-Lora.Q3_K_M.gguf b/Llama-3.2-1B-Creative-Lora.Q3_K_M.gguf new file mode 100644 index 0000000..c1246ed --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49516c43eed997572a651d0963db8a2174195db0539df2a9639f7013efbabe87 +size 690840448 diff --git a/Llama-3.2-1B-Creative-Lora.Q3_K_S.gguf b/Llama-3.2-1B-Creative-Lora.Q3_K_S.gguf new file mode 100644 index 0000000..8372313 --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6af96ab337677521470037ca79e957d1f7ffea00de1a4fac8347edfcfbbaac6 +size 641688448 diff --git a/Llama-3.2-1B-Creative-Lora.Q4_K_M.gguf b/Llama-3.2-1B-Creative-Lora.Q4_K_M.gguf new file mode 100644 index 0000000..ab3a251 --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dccb78f9418aba68a1d89c99b2801cb04f0ee698d0a6214ad9624cd7bc7de96 +size 807691136 diff --git a/Llama-3.2-1B-Creative-Lora.Q4_K_S.gguf b/Llama-3.2-1B-Creative-Lora.Q4_K_S.gguf new file mode 100644 index 0000000..709d101 --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c1c1ff6afc3efb71da44e0e8588d6742bfd2a71ba6643a3bc9fc9b02c0df93e +size 775644032 diff --git a/Llama-3.2-1B-Creative-Lora.Q5_K_M.gguf b/Llama-3.2-1B-Creative-Lora.Q5_K_M.gguf new file mode 100644 index 0000000..047e0ca --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2fcd8e11634f9f00bfce74caec2747d6b7830899a1467558aa2e053dbeceb3 +size 911500160 diff --git a/Llama-3.2-1B-Creative-Lora.Q5_K_S.gguf b/Llama-3.2-1B-Creative-Lora.Q5_K_S.gguf new file mode 100644 index 0000000..4a5d6d8 --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a5a53f23bb4c3ca082cdfe6d4ce4c00bedae266e7366070314c9d497a3093c +size 892560256 diff --git a/Llama-3.2-1B-Creative-Lora.Q6_K.gguf b/Llama-3.2-1B-Creative-Lora.Q6_K.gguf new file mode 100644 index 0000000..a143ee5 --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adfe2fc35d2b334f7479da4a90ad08921bc53c91d2a20028c8ce80f97c72ac0b +size 1021797248 diff --git a/Llama-3.2-1B-Creative-Lora.Q8_0.gguf b/Llama-3.2-1B-Creative-Lora.Q8_0.gguf new file mode 100644 index 0000000..b9e39a3 --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f400aadf23db2af2a69c267fd9f6448f14de53b2141b7295ae48eac108301af +size 1321079680 diff --git a/Llama-3.2-1B-Creative-Lora.f16.gguf b/Llama-3.2-1B-Creative-Lora.f16.gguf new file mode 100644 index 0000000..92f947f --- /dev/null +++ b/Llama-3.2-1B-Creative-Lora.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da3106fbecd27e04f00c6f92bbcb27a4538cc1121fe9db4cabd88d168c161d03 +size 2479592320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0b41c71 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: namissss/Llama-3.2-1B-Creative-Lora +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/namissss/Llama-3.2-1B-Creative-Lora + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-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-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Creative-Lora-GGUF/resolve/main/Llama-3.2-1B-Creative-Lora.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. + +