commit a1fbfb6870a371687536bccf70f4c554b30508d6 Author: ModelHub XC Date: Sat May 23 20:07:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-ItemWriter-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..45a224a --- /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-3.2-3B-ItemWriter.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ItemWriter.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ItemWriter.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ItemWriter.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ItemWriter.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ItemWriter.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ItemWriter.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ItemWriter.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ItemWriter.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ItemWriter.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ItemWriter.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-ItemWriter.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-ItemWriter.IQ4_XS.gguf b/Llama-3.2-3B-ItemWriter.IQ4_XS.gguf new file mode 100644 index 0000000..62ef2fc --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a56997186c36117083565f4555d9bfda68272a3c34ff90f3c1d09cdc00b9c2e +size 1840907200 diff --git a/Llama-3.2-3B-ItemWriter.Q2_K.gguf b/Llama-3.2-3B-ItemWriter.Q2_K.gguf new file mode 100644 index 0000000..8a42cef --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba193ebc3d9e8bbfa7aab7366cb0cd7b18a9a7b830103c75f816979ce63443a3 +size 1363936192 diff --git a/Llama-3.2-3B-ItemWriter.Q3_K_L.gguf b/Llama-3.2-3B-ItemWriter.Q3_K_L.gguf new file mode 100644 index 0000000..0f9ec99 --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a43daa6e33a45dcb83295e1cfc11928514e6d86e31cc93d1aa353b04adf5193a +size 1815348160 diff --git a/Llama-3.2-3B-ItemWriter.Q3_K_M.gguf b/Llama-3.2-3B-ItemWriter.Q3_K_M.gguf new file mode 100644 index 0000000..9d4596c --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb7bf159f336c1545d747d853ec5bb71a09beda09ecc51b4c0898dc9a79fd14 +size 1687159744 diff --git a/Llama-3.2-3B-ItemWriter.Q3_K_S.gguf b/Llama-3.2-3B-ItemWriter.Q3_K_S.gguf new file mode 100644 index 0000000..81b81af --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f1fc50606010f962ecd9dfcc57e8efcbaa56d7ef9aefc096084bf77308444c +size 1542849472 diff --git a/Llama-3.2-3B-ItemWriter.Q4_K_M.gguf b/Llama-3.2-3B-ItemWriter.Q4_K_M.gguf new file mode 100644 index 0000000..1a9e5a2 --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acba418ca690ed7a7bd8a692ca383889f5d32fb7facc5593122bf34cfecc7eba +size 2019378112 diff --git a/Llama-3.2-3B-ItemWriter.Q4_K_S.gguf b/Llama-3.2-3B-ItemWriter.Q4_K_S.gguf new file mode 100644 index 0000000..3233087 --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a98d79b80a3fb858599fd125b0dd72e56643239e23402d2245b46853f009217 +size 1928201152 diff --git a/Llama-3.2-3B-ItemWriter.Q5_K_M.gguf b/Llama-3.2-3B-ItemWriter.Q5_K_M.gguf new file mode 100644 index 0000000..587942e --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f228de02eae595e1df8c0aa7bc82773c53a785268fa08450065243ed1c34b2de +size 2322154432 diff --git a/Llama-3.2-3B-ItemWriter.Q5_K_S.gguf b/Llama-3.2-3B-ItemWriter.Q5_K_S.gguf new file mode 100644 index 0000000..58cc9f7 --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:545f59335571e561561708f5321ecd1ad9fbde47a6558d5fd492369974b2c04f +size 2269512640 diff --git a/Llama-3.2-3B-ItemWriter.Q6_K.gguf b/Llama-3.2-3B-ItemWriter.Q6_K.gguf new file mode 100644 index 0000000..446f673 --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:035c9c58792d56f0c75b067c955c3648f27c3649200beeb85958a70f8ea5124a +size 2643854272 diff --git a/Llama-3.2-3B-ItemWriter.Q8_0.gguf b/Llama-3.2-3B-ItemWriter.Q8_0.gguf new file mode 100644 index 0000000..a3011a0 --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f5503949b829158e8dc1174bf8ba6cda782c7d7587a83bbc5a4c96b33f408dd +size 3421899712 diff --git a/Llama-3.2-3B-ItemWriter.f16.gguf b/Llama-3.2-3B-ItemWriter.f16.gguf new file mode 100644 index 0000000..4d25111 --- /dev/null +++ b/Llama-3.2-3B-ItemWriter.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68544a59a89c392db5b76848aca013b3ee537877d572f64c577cb87d2db6e91a +size 6433688512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..13050d2 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: sheafyffe/Llama-3.2-3B-ItemWriter +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- personality +- psychology +- assessment +--- +## About + + + + + + +static quants of https://huggingface.co/sheafyffe/Llama-3.2-3B-ItemWriter + + +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-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-ItemWriter-GGUF/resolve/main/Llama-3.2-3B-ItemWriter.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. + +