commit e78af81566361b322c356865417c6a6f08915c5c Author: ModelHub XC Date: Thu May 7 12:27:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CreativeWriter-Llama3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..33dd679 --- /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 +CreativeWriter-Llama3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CreativeWriter-Llama3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CreativeWriter-Llama3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CreativeWriter-Llama3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CreativeWriter-Llama3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CreativeWriter-Llama3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CreativeWriter-Llama3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CreativeWriter-Llama3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CreativeWriter-Llama3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CreativeWriter-Llama3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CreativeWriter-Llama3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CreativeWriter-Llama3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CreativeWriter-Llama3.2-3B.IQ4_XS.gguf b/CreativeWriter-Llama3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..b7ff3e6 --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96a3afbb25cc9752eacad5203400cfe7fbef4080e557788a89e48b4fda54ebe +size 1840908288 diff --git a/CreativeWriter-Llama3.2-3B.Q2_K.gguf b/CreativeWriter-Llama3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..4d0dd9e --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f53a78287751f0b3d504466dd3604e94269953eb3a691318bd19a48dd136e4 +size 1363937280 diff --git a/CreativeWriter-Llama3.2-3B.Q3_K_L.gguf b/CreativeWriter-Llama3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..ea92acc --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea3db5fcf440e2fff73c32276cd9a993aa9c2149b43ab69933ba41e448ed8488 +size 1815349248 diff --git a/CreativeWriter-Llama3.2-3B.Q3_K_M.gguf b/CreativeWriter-Llama3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..a990beb --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b7104a5daba1627b5077de7c78eede61b451db2caca982ed37e272bcc7fae5 +size 1687160832 diff --git a/CreativeWriter-Llama3.2-3B.Q3_K_S.gguf b/CreativeWriter-Llama3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..7700c70 --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e4a8956d5230f681f0a6ada9e8d293b8952b59a2c5e72c546390adbe44aeb1f +size 1542850560 diff --git a/CreativeWriter-Llama3.2-3B.Q4_K_M.gguf b/CreativeWriter-Llama3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..20fca2e --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:087176cf4db9fb953f15a1aea95f9c59498c74d22cdd00221a44c102340c1fdf +size 2019379200 diff --git a/CreativeWriter-Llama3.2-3B.Q4_K_S.gguf b/CreativeWriter-Llama3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..bf775ba --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6aad0500deafedf492834332fff9c67f74dc0a6fcbfd6c2cc089335bfd9155f +size 1928202240 diff --git a/CreativeWriter-Llama3.2-3B.Q5_K_M.gguf b/CreativeWriter-Llama3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..e73975c --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b719b6a278faadfeb3b899c32df07334ed896778e6b4c436bf5bea5708642cae +size 2322155520 diff --git a/CreativeWriter-Llama3.2-3B.Q5_K_S.gguf b/CreativeWriter-Llama3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..4c1a976 --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5eb76ebff52ff745f66f8d7040bb7ac3f25dc061149083f2ac8615e74497e1 +size 2269513728 diff --git a/CreativeWriter-Llama3.2-3B.Q6_K.gguf b/CreativeWriter-Llama3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..3c47b3b --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5645eebf766202fa97063544132cb0e51d89a6e1c438632f203c8b3a1b9ae68b +size 2643855360 diff --git a/CreativeWriter-Llama3.2-3B.Q8_0.gguf b/CreativeWriter-Llama3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..edead4a --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34ea16ae554dcf86086c775c001140b2e9a14c91091c93a983e645ce27fc9a02 +size 3421900800 diff --git a/CreativeWriter-Llama3.2-3B.f16.gguf b/CreativeWriter-Llama3.2-3B.f16.gguf new file mode 100644 index 0000000..de4ccff --- /dev/null +++ b/CreativeWriter-Llama3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc41671f6322dd3210db8889dfcb39bdeb2da22a6b2daf4f065887b9ce554f8f +size 6433689600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..24fe2c0 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: theprint/CreativeWriter-Llama3.2-3B +datasets: +- theprint/AuthorsAssistant +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/theprint/CreativeWriter-Llama3.2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CreativeWriter-Llama3.2-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-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/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CreativeWriter-Llama3.2-3B-GGUF/resolve/main/CreativeWriter-Llama3.2-3B.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. + +