commit 9bbd9031e80a2a363a9b4ecc89d882467f653584 Author: ModelHub XC Date: Tue Jul 21 07:43:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..125245c --- /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-merged-base-3K-updated.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-merged-base-3K-updated.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-merged-base-3K-updated.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-merged-base-3K-updated.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-merged-base-3K-updated.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-merged-base-3K-updated.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-merged-base-3K-updated.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-merged-base-3K-updated.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-merged-base-3K-updated.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-merged-base-3K-updated.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-merged-base-3K-updated.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-merged-base-3K-updated.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1e85f47 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: milan44/llama-3.2-3b-merged-base-3K-updated +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/milan44/llama-3.2-3b-merged-base-3K-updated + + +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-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-merged-base-3K-updated-GGUF/resolve/main/llama-3.2-3b-merged-base-3K-updated.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. + + diff --git a/llama-3.2-3b-merged-base-3K-updated.IQ4_XS.gguf b/llama-3.2-3b-merged-base-3K-updated.IQ4_XS.gguf new file mode 100644 index 0000000..f966373 --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c257fb20d2dced97d7fd13b5d86a23140416477b48aac102de7adc1daaa17d8 +size 1840908288 diff --git a/llama-3.2-3b-merged-base-3K-updated.Q2_K.gguf b/llama-3.2-3b-merged-base-3K-updated.Q2_K.gguf new file mode 100644 index 0000000..7beac28 --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2a210c9de785923bc18c0c9c694ca09b261dfcb52e2ab4f6bb2caefa68ad2db +size 1363937280 diff --git a/llama-3.2-3b-merged-base-3K-updated.Q3_K_L.gguf b/llama-3.2-3b-merged-base-3K-updated.Q3_K_L.gguf new file mode 100644 index 0000000..e8ae356 --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1df45ecd1a52778b75f6069119328ac18359100b76b61cd56e41d7cf592c239d +size 1815349248 diff --git a/llama-3.2-3b-merged-base-3K-updated.Q3_K_M.gguf b/llama-3.2-3b-merged-base-3K-updated.Q3_K_M.gguf new file mode 100644 index 0000000..db9c049 --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378d4a6c848f87fd719315c5a0ad82ad0b513c986e34c5631eca77a7825d829c +size 1687160832 diff --git a/llama-3.2-3b-merged-base-3K-updated.Q3_K_S.gguf b/llama-3.2-3b-merged-base-3K-updated.Q3_K_S.gguf new file mode 100644 index 0000000..21a40e5 --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a53843d36694583cec43c157dd4d28a58f1b7dc1ebd6b574cc7431a5d86e04c6 +size 1542850560 diff --git a/llama-3.2-3b-merged-base-3K-updated.Q4_K_M.gguf b/llama-3.2-3b-merged-base-3K-updated.Q4_K_M.gguf new file mode 100644 index 0000000..5ed8eab --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6604d31042137689a2c43fec45da85ccb6a249d1a05bc6bddcb8f1634ff3c678 +size 2019379200 diff --git a/llama-3.2-3b-merged-base-3K-updated.Q4_K_S.gguf b/llama-3.2-3b-merged-base-3K-updated.Q4_K_S.gguf new file mode 100644 index 0000000..45ec01f --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d092168360fdb9346031c95efdcec0d1dbd65bbc9107ff4f949f5984b142638a +size 1928202240 diff --git a/llama-3.2-3b-merged-base-3K-updated.Q5_K_M.gguf b/llama-3.2-3b-merged-base-3K-updated.Q5_K_M.gguf new file mode 100644 index 0000000..6cf806a --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac004fc181085aa39c77c3440010274052b07154b799bebc8849c2ad7131479 +size 2322155520 diff --git a/llama-3.2-3b-merged-base-3K-updated.Q5_K_S.gguf b/llama-3.2-3b-merged-base-3K-updated.Q5_K_S.gguf new file mode 100644 index 0000000..1cc93ce --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f665adf0ce29f380b5e5a182cf2421b45434aebaf697cfe3a670e29c9b4608c4 +size 2269513728 diff --git a/llama-3.2-3b-merged-base-3K-updated.Q6_K.gguf b/llama-3.2-3b-merged-base-3K-updated.Q6_K.gguf new file mode 100644 index 0000000..e19d322 --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:029eecd57a06cfb26e187c34fbca31a4865c325e0b8ef2e335e454c2ec03fa2f +size 2643855360 diff --git a/llama-3.2-3b-merged-base-3K-updated.Q8_0.gguf b/llama-3.2-3b-merged-base-3K-updated.Q8_0.gguf new file mode 100644 index 0000000..8346cb4 --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc9e1a62f51347045ac76959bbf8ebaee5466426a34d084d3745ca982bfeef2 +size 3421902272 diff --git a/llama-3.2-3b-merged-base-3K-updated.f16.gguf b/llama-3.2-3b-merged-base-3K-updated.f16.gguf new file mode 100644 index 0000000..7c1b046 --- /dev/null +++ b/llama-3.2-3b-merged-base-3K-updated.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3e018562a36bd8d9230972a5ae024b4bdfa0481033fafedf04263ab7e1128a5 +size 6433696832