commit 478f0a9b0011a93c4fc0a61902caf6f23d105b37 Author: ModelHub XC Date: Mon Aug 3 13:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-RP-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d8bcdac --- /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-Instruct-RP.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RP.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RP.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RP.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RP.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RP.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RP.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RP.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RP.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RP.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RP.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RP.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-RP.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-RP.IQ4_XS.gguf new file mode 100644 index 0000000..ebeba48 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1137d11422dfb08379f3306e5cf2ac8c797ed5e85dd0390ecdccb8000d5bded5 +size 748384928 diff --git a/Llama-3.2-1B-Instruct-RP.Q2_K.gguf b/Llama-3.2-1B-Instruct-RP.Q2_K.gguf new file mode 100644 index 0000000..d4fba3d --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:371f3a14d9c6809de956b4198765c0a7c49e194431ecc62b387b029ffd71fb2d +size 580874912 diff --git a/Llama-3.2-1B-Instruct-RP.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-RP.Q3_K_L.gguf new file mode 100644 index 0000000..6db69e2 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155a28ee6cf7882222ff6b84df6fc099ee14b5b7e263727d3ef7171a3caf15b9 +size 732525216 diff --git a/Llama-3.2-1B-Instruct-RP.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-RP.Q3_K_M.gguf new file mode 100644 index 0000000..3357953 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:740d6512d1c2982d35d5d734ff8f5506207d65a9c27f05358d6fc2b877ebb50b +size 690844320 diff --git a/Llama-3.2-1B-Instruct-RP.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-RP.Q3_K_S.gguf new file mode 100644 index 0000000..95b8b8c --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d39bc936bb9beb7592fd3959ee7bd69bb5763d19b0ff8053f43033f1fd6ce871 +size 641692320 diff --git a/Llama-3.2-1B-Instruct-RP.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-RP.Q4_K_M.gguf new file mode 100644 index 0000000..be5aca9 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:217c43503dec3c6e3e08cfaa0477866de597d87292513240c5819d54b4f707ba +size 807695008 diff --git a/Llama-3.2-1B-Instruct-RP.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-RP.Q4_K_S.gguf new file mode 100644 index 0000000..da7dcac --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:866339af41cb23de33fe9b50aeda6f9cfeb8689784bc1a4eacc2fa40595125a6 +size 775647904 diff --git a/Llama-3.2-1B-Instruct-RP.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-RP.Q5_K_M.gguf new file mode 100644 index 0000000..4da75eb --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:673f16bce09d7d99e30b7c7d8bf1c9b591c64baecdb698751079b10479e276e9 +size 911504032 diff --git a/Llama-3.2-1B-Instruct-RP.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-RP.Q5_K_S.gguf new file mode 100644 index 0000000..368a3d1 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7126c6d6207be4ee372406a47f83658f5ffe9617ff338e77fa03278d1b9ab5b1 +size 892564128 diff --git a/Llama-3.2-1B-Instruct-RP.Q6_K.gguf b/Llama-3.2-1B-Instruct-RP.Q6_K.gguf new file mode 100644 index 0000000..3a81005 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f6e50747b14c26d20a7855742ad122d81e96e767f14853260a69eb690a12509 +size 1021801120 diff --git a/Llama-3.2-1B-Instruct-RP.Q8_0.gguf b/Llama-3.2-1B-Instruct-RP.Q8_0.gguf new file mode 100644 index 0000000..8741f1b --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c555b6bded5c7dbaf967443d7ea22cc1a646a2cdc5ad5101128d521fa08e3147 +size 1321083552 diff --git a/Llama-3.2-1B-Instruct-RP.f16.gguf b/Llama-3.2-1B-Instruct-RP.f16.gguf new file mode 100644 index 0000000..b5cd3da --- /dev/null +++ b/Llama-3.2-1B-Instruct-RP.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378bd524585b524e6eca72d887d9e7b3602a68bc52a986c4ccff88f13902d37d +size 2479596192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..11ae861 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/Llama-3.2-1B-Instruct-RP +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.2-1B-Instruct-RP + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-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-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RP-GGUF/resolve/main/Llama-3.2-1B-Instruct-RP.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. + +