commit eaa580486771dee9a0e9f43b397777c8297abcd0 Author: ModelHub XC Date: Mon Sep 28 06:39:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-RS-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f48ce7b --- /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-RS.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RS.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RS.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RS.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RS.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RS.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RS.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RS.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RS.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RS.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RS.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-RS.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-RS.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-RS.IQ4_XS.gguf new file mode 100644 index 0000000..68241e5 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20db2410e7125d3de35c6111b686fbaceb4f98048cfecca90dbae4de44546013 +size 748388704 diff --git a/Llama-3.2-1B-Instruct-RS.Q2_K.gguf b/Llama-3.2-1B-Instruct-RS.Q2_K.gguf new file mode 100644 index 0000000..da25837 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36791032efc67f0518a0d163cc72b6fb0d1c52d8c231bf7499fdd619046cda88 +size 580878688 diff --git a/Llama-3.2-1B-Instruct-RS.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-RS.Q3_K_L.gguf new file mode 100644 index 0000000..f3d84bc --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2f24ce0e018cbae3755fdc48aea4ab6fe37248093e414bf40393ce0a34c257d +size 732528992 diff --git a/Llama-3.2-1B-Instruct-RS.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-RS.Q3_K_M.gguf new file mode 100644 index 0000000..f2e9a75 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b711513e283a88f9abe2a74b374d4d18edeb1d32a7ecec9750e58768e77c2c58 +size 690848096 diff --git a/Llama-3.2-1B-Instruct-RS.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-RS.Q3_K_S.gguf new file mode 100644 index 0000000..7dcc7ca --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:514baecd83ad4aeaf25f79f7c62c34a8ed8fc4da7804f31ccab5c7db07d2f81d +size 641696096 diff --git a/Llama-3.2-1B-Instruct-RS.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-RS.Q4_K_M.gguf new file mode 100644 index 0000000..0fb63bf --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ead703570bdd235a20f16c4eb3ba74bb25c1247d1ee3c2c31a0d02240fbfaa6f +size 807698784 diff --git a/Llama-3.2-1B-Instruct-RS.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-RS.Q4_K_S.gguf new file mode 100644 index 0000000..09ea98b --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a3defe47f4cdbf86b677ad1657283179af4ae304832d14d9730b3300b82216b +size 775651680 diff --git a/Llama-3.2-1B-Instruct-RS.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-RS.Q5_K_M.gguf new file mode 100644 index 0000000..a2aafb2 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0111aa38ad337b0dfc8cd4a7fbdaeb10669f70489c03491fb69b2db09c5d9c2 +size 911507808 diff --git a/Llama-3.2-1B-Instruct-RS.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-RS.Q5_K_S.gguf new file mode 100644 index 0000000..f8a8410 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52390dd52cf16da6697b4d7ec3a3b09feaa621e06ee62bdce3e6ee013c2bc7c7 +size 892567904 diff --git a/Llama-3.2-1B-Instruct-RS.Q6_K.gguf b/Llama-3.2-1B-Instruct-RS.Q6_K.gguf new file mode 100644 index 0000000..0b1940e --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5aa5a794d4e777c7501dcd1ed08a49b79b7cbc05ffeb9113e39dc20b872d04 +size 1021804896 diff --git a/Llama-3.2-1B-Instruct-RS.Q8_0.gguf b/Llama-3.2-1B-Instruct-RS.Q8_0.gguf new file mode 100644 index 0000000..857855a --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:855a7bea99aacc4aadaebbd6438f6ce4a38a1fb6f83bbce51032ae3c38653a89 +size 1321087328 diff --git a/Llama-3.2-1B-Instruct-RS.f16.gguf b/Llama-3.2-1B-Instruct-RS.f16.gguf new file mode 100644 index 0000000..348b8c9 --- /dev/null +++ b/Llama-3.2-1B-Instruct-RS.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9987d22f4bb3b06b35cd3cbc718fcfd5f4bedbb6ab1014bfa49abe159fa9713b +size 2479599968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8bd3641 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: CountZero404/Llama-3.2-1B-Instruct-RS +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/CountZero404/Llama-3.2-1B-Instruct-RS + + +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-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-RS-GGUF/resolve/main/Llama-3.2-1B-Instruct-RS.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. + +