commit d4e3c8ba88980bd231fff47cbe93816fb40d2e1b Author: ModelHub XC Date: Tue Sep 29 01:33:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B_sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d682789 --- /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_sft.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B_sft.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B_sft.IQ4_XS.gguf b/Llama-3.2-3B_sft.IQ4_XS.gguf new file mode 100644 index 0000000..51fce8c --- /dev/null +++ b/Llama-3.2-3B_sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eb333e7bf24a748655529abe914ad28f090d5ed4ad7855cc9651f8966a37d9b +size 1840906816 diff --git a/Llama-3.2-3B_sft.Q2_K.gguf b/Llama-3.2-3B_sft.Q2_K.gguf new file mode 100644 index 0000000..31dfa2d --- /dev/null +++ b/Llama-3.2-3B_sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ec2fc96505c988381939c59cf4a473fe380717b4f332ae80aaafe1724739e3 +size 1363935808 diff --git a/Llama-3.2-3B_sft.Q3_K_L.gguf b/Llama-3.2-3B_sft.Q3_K_L.gguf new file mode 100644 index 0000000..0063714 --- /dev/null +++ b/Llama-3.2-3B_sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:304c21ca46801b8b376941b9e408def4f33a10ac7ba1443f0fcc906a2aeb0210 +size 1815347776 diff --git a/Llama-3.2-3B_sft.Q3_K_M.gguf b/Llama-3.2-3B_sft.Q3_K_M.gguf new file mode 100644 index 0000000..2bef962 --- /dev/null +++ b/Llama-3.2-3B_sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdde170dea2505db7e6ab4c35ff964110fa04b5aa87ca06a4be46a365afb37d7 +size 1687159360 diff --git a/Llama-3.2-3B_sft.Q3_K_S.gguf b/Llama-3.2-3B_sft.Q3_K_S.gguf new file mode 100644 index 0000000..3039251 --- /dev/null +++ b/Llama-3.2-3B_sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e2476fd42fc8aa25a5827d58e8e45e4b4dbaee497b266796707bedbce4db08 +size 1542849088 diff --git a/Llama-3.2-3B_sft.Q4_0_4_4.gguf b/Llama-3.2-3B_sft.Q4_0_4_4.gguf new file mode 100644 index 0000000..41e37fc --- /dev/null +++ b/Llama-3.2-3B_sft.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb533c9b6f03a5b5ad1e77ca794cb3ffd794546dfe71f6679e1ca734472b3fa5 +size 1917190720 diff --git a/Llama-3.2-3B_sft.Q4_K_M.gguf b/Llama-3.2-3B_sft.Q4_K_M.gguf new file mode 100644 index 0000000..1b54935 --- /dev/null +++ b/Llama-3.2-3B_sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6795b6beb6e132c55b017358bb0b8d0fddbd1dee22d8573575a512c7fd5acd +size 2019377728 diff --git a/Llama-3.2-3B_sft.Q4_K_S.gguf b/Llama-3.2-3B_sft.Q4_K_S.gguf new file mode 100644 index 0000000..1d6e068 --- /dev/null +++ b/Llama-3.2-3B_sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d85269eb0737bd3af71c75a3f5b02363cc56876538b0377e72cbd7b1f4f78af +size 1928200768 diff --git a/Llama-3.2-3B_sft.Q5_K_M.gguf b/Llama-3.2-3B_sft.Q5_K_M.gguf new file mode 100644 index 0000000..d40ca1a --- /dev/null +++ b/Llama-3.2-3B_sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09b4649f50a5b43c90631f083bb62f2b948c93e423a3c321d1229f92378f29e4 +size 2322154048 diff --git a/Llama-3.2-3B_sft.Q5_K_S.gguf b/Llama-3.2-3B_sft.Q5_K_S.gguf new file mode 100644 index 0000000..aa4ed81 --- /dev/null +++ b/Llama-3.2-3B_sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b9f072823cb8c4d501c863ebd9e14179d7cafe39351c9e10dae0332dc093eec +size 2269512256 diff --git a/Llama-3.2-3B_sft.Q6_K.gguf b/Llama-3.2-3B_sft.Q6_K.gguf new file mode 100644 index 0000000..d1b405a --- /dev/null +++ b/Llama-3.2-3B_sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a11ad336a2f5c9cd9bea2f236fe15e9e2b7c7ce61ba7575c759079e4f946ab5c +size 2643853888 diff --git a/Llama-3.2-3B_sft.Q8_0.gguf b/Llama-3.2-3B_sft.Q8_0.gguf new file mode 100644 index 0000000..a7f2428 --- /dev/null +++ b/Llama-3.2-3B_sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09b63dec275cc1fb035d8a8c24933dc95a6c1a8b1f7210803eced23c834c4271 +size 3421899328 diff --git a/Llama-3.2-3B_sft.f16.gguf b/Llama-3.2-3B_sft.f16.gguf new file mode 100644 index 0000000..4595b43 --- /dev/null +++ b/Llama-3.2-3B_sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff8c2ffe957edb6ccfffe9f9c9b4ea606f7dd9bfba46f02cbd1dc8fd7411c4df +size 6433688128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b8a1329 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: KSU-HW-SEC/Llama-3.2-3B_sft +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/KSU-HW-SEC/Llama-3.2-3B_sft + + +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_sft-GGUF/resolve/main/Llama-3.2-3B_sft.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B_sft-GGUF/resolve/main/Llama-3.2-3B_sft.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B_sft-GGUF/resolve/main/Llama-3.2-3B_sft.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B_sft-GGUF/resolve/main/Llama-3.2-3B_sft.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B_sft-GGUF/resolve/main/Llama-3.2-3B_sft.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B_sft-GGUF/resolve/main/Llama-3.2-3B_sft.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_sft-GGUF/resolve/main/Llama-3.2-3B_sft.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B_sft-GGUF/resolve/main/Llama-3.2-3B_sft.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B_sft-GGUF/resolve/main/Llama-3.2-3B_sft.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B_sft-GGUF/resolve/main/Llama-3.2-3B_sft.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B_sft-GGUF/resolve/main/Llama-3.2-3B_sft.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B_sft-GGUF/resolve/main/Llama-3.2-3B_sft.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B_sft-GGUF/resolve/main/Llama-3.2-3B_sft.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. + +