commit 0864fe44c0c4b87e98b4b1afbd7cec72e0f7e7a3 Author: ModelHub XC Date: Wed Aug 5 21:21:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ddfac5a --- /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-3.2-1B-Instruct-commonsense_qa.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-commonsense_qa.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-commonsense_qa.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-commonsense_qa.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-commonsense_qa.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-commonsense_qa.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-commonsense_qa.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-commonsense_qa.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-commonsense_qa.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.IQ4_XS.gguf new file mode 100644 index 0000000..a74f20f --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09bc737daaacdb7a6d34dd679dbd4a02f2ce93ac0d854b826e9f129f7bf925b1 +size 748382208 diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.Q2_K.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.Q2_K.gguf new file mode 100644 index 0000000..5fde888 --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c5c244466f3ff4acf5ee6284a7d5e4bc23f83f407793b75aceb346c1c7a0db4 +size 580872192 diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_L.gguf new file mode 100644 index 0000000..44f42b6 --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f201c57b93355217363c59a9fbe72eccff50e7b3729134a009f9e80b6e9525ce +size 732522496 diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_M.gguf new file mode 100644 index 0000000..7c63978 --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d01b7a63bbcda1d98504dd3c4e1fc68dafeb7643df9d91fe270b55d3d8c3386a +size 690841600 diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_S.gguf new file mode 100644 index 0000000..a49ec36 --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c32e4a445de44606d080916082c36b960c7edda4e5e6b48bf7fa683fd58c1f4 +size 641689600 diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.Q4_K_M.gguf new file mode 100644 index 0000000..4823180 --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4555c221473b476bd6edea5091238a0169d83ebdfa444acfbb57f4dab411668 +size 807692288 diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.Q4_K_S.gguf new file mode 100644 index 0000000..7fc789f --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4c43506bb01ead3d6a6c0a08c384374a3d8f1103da2bef2c61d47f47b1db70f +size 775645184 diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.Q5_K_M.gguf new file mode 100644 index 0000000..843a275 --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb6afb224c91b5cf2857172917b633cc4a34828ce3badf51a8203d39aea62e3 +size 911501312 diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.Q5_K_S.gguf new file mode 100644 index 0000000..51f0ccc --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c9d7ce83b76f647180593d5220c8c38f73cf97c1b459be35e231e98e0a4f5a6 +size 892561408 diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.Q6_K.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.Q6_K.gguf new file mode 100644 index 0000000..5ed8674 --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1132e10a5788c3494c04c9e411d9d7e83b300c2134f8c66a06712ea65597c13 +size 1021798400 diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.Q8_0.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.Q8_0.gguf new file mode 100644 index 0000000..94bae3b --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d4562f5562e7a647cfd4d2760c7355aab9ac43418d8d938dde24b2974cc4539 +size 1321081312 diff --git a/Llama-3.2-1B-Instruct-commonsense_qa.f16.gguf b/Llama-3.2-1B-Instruct-commonsense_qa.f16.gguf new file mode 100644 index 0000000..063973c --- /dev/null +++ b/Llama-3.2-1B-Instruct-commonsense_qa.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb56f5a3f4d4a26d0d1e57f65ab8283b6afec1f2dcedac9cb8edc7e4a03f706d +size 2479595872 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b50ea63 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: ank028/Llama-3.2-1B-Instruct-commonsense_qa +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/ank028/Llama-3.2-1B-Instruct-commonsense_qa + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-Instruct-commonsense_qa-GGUF).*** + +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-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-commonsense_qa-GGUF/resolve/main/Llama-3.2-1B-Instruct-commonsense_qa.f16.gguf) | f16 | 2.6 | 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. + +