commit ba6b4abf06739abe96fb620d6b135b63877967e8 Author: ModelHub XC Date: Wed Jun 3 23:20:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ec528e2 --- /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 +Llama3.2-1B-RolePlaying-Full.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-RolePlaying-Full.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-RolePlaying-Full.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-RolePlaying-Full.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-RolePlaying-Full.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-RolePlaying-Full.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-RolePlaying-Full.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-RolePlaying-Full.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-RolePlaying-Full.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-RolePlaying-Full.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-RolePlaying-Full.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-RolePlaying-Full.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-1B-RolePlaying-Full.IQ4_XS.gguf b/Llama3.2-1B-RolePlaying-Full.IQ4_XS.gguf new file mode 100644 index 0000000..b26c375 --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e838b2edc87c2b415636c81512359fa847df181492569b97d75520667eabea0 +size 748385952 diff --git a/Llama3.2-1B-RolePlaying-Full.Q2_K.gguf b/Llama3.2-1B-RolePlaying-Full.Q2_K.gguf new file mode 100644 index 0000000..6eb47ba --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b0b88445e82124369918fe7df38300f9de18aa861ebc99f4094dd7ae8c84782 +size 580875936 diff --git a/Llama3.2-1B-RolePlaying-Full.Q3_K_L.gguf b/Llama3.2-1B-RolePlaying-Full.Q3_K_L.gguf new file mode 100644 index 0000000..67dc107 --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5037bfaa06fa852471c2601502d8f23313f1822d984c5d93cd8517911f6e6aba +size 732526240 diff --git a/Llama3.2-1B-RolePlaying-Full.Q3_K_M.gguf b/Llama3.2-1B-RolePlaying-Full.Q3_K_M.gguf new file mode 100644 index 0000000..e058094 --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e0d6683c7c04bac6dab1d6adf6a493caed782d99cd60c9d54f4d05804ea7949 +size 690845344 diff --git a/Llama3.2-1B-RolePlaying-Full.Q3_K_S.gguf b/Llama3.2-1B-RolePlaying-Full.Q3_K_S.gguf new file mode 100644 index 0000000..1b13663 --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16018780d94358c2ee367672ea14ecd7233baf296ae7cd42901207dd768b3104 +size 641693344 diff --git a/Llama3.2-1B-RolePlaying-Full.Q4_K_M.gguf b/Llama3.2-1B-RolePlaying-Full.Q4_K_M.gguf new file mode 100644 index 0000000..e3973e4 --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965e3fbee6a241b066e3a56df4e2b16177093b905e1683fd34fdb1d82bbea935 +size 807696032 diff --git a/Llama3.2-1B-RolePlaying-Full.Q4_K_S.gguf b/Llama3.2-1B-RolePlaying-Full.Q4_K_S.gguf new file mode 100644 index 0000000..bacd371 --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2053b0ddd2b204a194a140cd123d5aba8320ee64d77809ee82b640480d5671 +size 775648928 diff --git a/Llama3.2-1B-RolePlaying-Full.Q5_K_M.gguf b/Llama3.2-1B-RolePlaying-Full.Q5_K_M.gguf new file mode 100644 index 0000000..2aec652 --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:884ae3b3455e8ba33f088a98d6a54838b2c0608c1752d5f2041830213b94e81c +size 911505056 diff --git a/Llama3.2-1B-RolePlaying-Full.Q5_K_S.gguf b/Llama3.2-1B-RolePlaying-Full.Q5_K_S.gguf new file mode 100644 index 0000000..2393bb9 --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4ca2d1dcbe189b00e6ef6fc4e9fb48873768893be910210fbebbe9bdbb53e5 +size 892565152 diff --git a/Llama3.2-1B-RolePlaying-Full.Q6_K.gguf b/Llama3.2-1B-RolePlaying-Full.Q6_K.gguf new file mode 100644 index 0000000..c0a265a --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1781a389e6ab30303861b99601f414388221a607f2938156ffbf43a589e15890 +size 1021802144 diff --git a/Llama3.2-1B-RolePlaying-Full.Q8_0.gguf b/Llama3.2-1B-RolePlaying-Full.Q8_0.gguf new file mode 100644 index 0000000..a359ac8 --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3c8554618c7300c685558077f1bae29dbcef45b8f262b8d6b6f9ac1a5c0a3bc +size 1321084576 diff --git a/Llama3.2-1B-RolePlaying-Full.f16.gguf b/Llama3.2-1B-RolePlaying-Full.f16.gguf new file mode 100644 index 0000000..c2dc04d --- /dev/null +++ b/Llama3.2-1B-RolePlaying-Full.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19e832bf17b5f7b87562415ebf88f8b6b560b4907644f5a4af819607d6ae3580 +size 2479597216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bec8d0d --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: theprint/Llama3.2-1B-RolePlaying-Full +datasets: +- theprint/RolePlaying +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/theprint/Llama3.2-1B-RolePlaying-Full + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.2-1B-RolePlaying-Full-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-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/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-RolePlaying-Full-GGUF/resolve/main/Llama3.2-1B-RolePlaying-Full.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. + +