commit 3231e6c7801ab585afe2d5e23b1efe85c508def0 Author: ModelHub XC Date: Sun Aug 2 03:54:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2-3b-komedic-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7c5ffb8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-komedic-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-komedic-instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7289fc1 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: unidocs/llama-3.2-3b-komedic-instruct +language: +- en +- ko +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- medical +- healthcare +--- +## About + + + + + + +static quants of https://huggingface.co/unidocs/llama-3.2-3b-komedic-instruct + + +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-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-komedic-instruct-GGUF/resolve/main/llama-3.2-3b-komedic-instruct.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/llama-3.2-3b-komedic-instruct.IQ4_XS.gguf b/llama-3.2-3b-komedic-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..76505d6 --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94079c1435464041068244bc19798e50b62d698756549c88b9f856548c59e9ce +size 1840907200 diff --git a/llama-3.2-3b-komedic-instruct.Q2_K.gguf b/llama-3.2-3b-komedic-instruct.Q2_K.gguf new file mode 100644 index 0000000..4030e7b --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0cd9249a6361310ed66fe49efac20ec6bdbf08b0241b915cc2783c70500ff4 +size 1363936192 diff --git a/llama-3.2-3b-komedic-instruct.Q3_K_L.gguf b/llama-3.2-3b-komedic-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..625deff --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6bdfa195cf7063123229c563e01364c48d26f557869faf53755538998b050c4 +size 1815348160 diff --git a/llama-3.2-3b-komedic-instruct.Q3_K_M.gguf b/llama-3.2-3b-komedic-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..47045a8 --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0992fe8f8557445ee05e28a0766a628bbfff868be688680083d4ffe54b125969 +size 1687159744 diff --git a/llama-3.2-3b-komedic-instruct.Q3_K_S.gguf b/llama-3.2-3b-komedic-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..17c7c21 --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e2c30849cc4d12ed1e9fb04c465223962fce0223fea63891f1edbc2df6f21d +size 1542849472 diff --git a/llama-3.2-3b-komedic-instruct.Q4_0_4_4.gguf b/llama-3.2-3b-komedic-instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..8aa37d1 --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:560e062238141396b078aa3cb57790cd5c786de306248103c40d5b320e9f06af +size 1917191104 diff --git a/llama-3.2-3b-komedic-instruct.Q4_K_M.gguf b/llama-3.2-3b-komedic-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..95ebb34 --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b6010fe3634091fa5b9a71785450cc8d365bdacf853b61832f323b72f58f64c +size 2019378112 diff --git a/llama-3.2-3b-komedic-instruct.Q4_K_S.gguf b/llama-3.2-3b-komedic-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..bff249e --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d85826dfaab3d455424d3407ff03bd3aa6cbb15849df7c28c5a472dbb460943 +size 1928201152 diff --git a/llama-3.2-3b-komedic-instruct.Q5_K_M.gguf b/llama-3.2-3b-komedic-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..4220c89 --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbdf5636563851726c279f9f432047a889e8a4f90da84b57439721c7d9bce691 +size 2322154432 diff --git a/llama-3.2-3b-komedic-instruct.Q5_K_S.gguf b/llama-3.2-3b-komedic-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..2ba17ed --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a0d27fd860840cd425da17b0b0a63f5e4d50427db724218483a7ef6eb4783bf +size 2269512640 diff --git a/llama-3.2-3b-komedic-instruct.Q6_K.gguf b/llama-3.2-3b-komedic-instruct.Q6_K.gguf new file mode 100644 index 0000000..0b66f8e --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e17d7a28070e67d611707319e62b505a0027601277d768fe25c11bb0e7ebcc1 +size 2643854272 diff --git a/llama-3.2-3b-komedic-instruct.Q8_0.gguf b/llama-3.2-3b-komedic-instruct.Q8_0.gguf new file mode 100644 index 0000000..f206cde --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e82e68549f1e7cf95fcad0c8fe2e8fbae47f932405526074dc9d59d9a4ca0178 +size 3421899712 diff --git a/llama-3.2-3b-komedic-instruct.f16.gguf b/llama-3.2-3b-komedic-instruct.f16.gguf new file mode 100644 index 0000000..dfc294d --- /dev/null +++ b/llama-3.2-3b-komedic-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab335b5f10b4084738fcf5d3cf1fbe4098b6258ec0173698b25994803d15622b +size 6433688512