commit 101f663e8be41035bebb16fda6b978e62de9423d Author: ModelHub XC Date: Thu Apr 30 08:31:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..68e2c00 --- /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 +Alpaca-Llama-3.2-1B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-Llama-3.2-1B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-Llama-3.2-1B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-Llama-3.2-1B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-Llama-3.2-1B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-Llama-3.2-1B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-Llama-3.2-1B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-Llama-3.2-1B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-Llama-3.2-1B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-Llama-3.2-1B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-Llama-3.2-1B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-Llama-3.2-1B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Alpaca-Llama-3.2-1B-Instruct.IQ4_XS.gguf b/Alpaca-Llama-3.2-1B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..518946d --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4406a0453c2efadc5b9a50fcd6055db3f5c0fc34c61d76b37caa083d9a889110 +size 748381088 diff --git a/Alpaca-Llama-3.2-1B-Instruct.Q2_K.gguf b/Alpaca-Llama-3.2-1B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..66b0926 --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04a59e996e8c32bc04f5c161abe204c45a25200f16f89d6b887e210e7f78a68 +size 580871072 diff --git a/Alpaca-Llama-3.2-1B-Instruct.Q3_K_L.gguf b/Alpaca-Llama-3.2-1B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..16079eb --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb034cf534280cab3c85cbfff859adb7ca4abb2c5c75db9af55033e0f28b7a0 +size 732521376 diff --git a/Alpaca-Llama-3.2-1B-Instruct.Q3_K_M.gguf b/Alpaca-Llama-3.2-1B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..56aa5be --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e51e0220f4709e7bd54deb467c19e792808e0644689d6b467304876980f39a +size 690840480 diff --git a/Alpaca-Llama-3.2-1B-Instruct.Q3_K_S.gguf b/Alpaca-Llama-3.2-1B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..a850ebf --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:997db8eb3169cfea97c88e66ae46aa10ce5adbf5614397f09b3aca1aaf378d00 +size 641688480 diff --git a/Alpaca-Llama-3.2-1B-Instruct.Q4_K_M.gguf b/Alpaca-Llama-3.2-1B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f5be1a9 --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f4b16365e10e68b1e41a155ec3e5fb4e47acc9c18ab7392f6af2cfecf90943 +size 807691168 diff --git a/Alpaca-Llama-3.2-1B-Instruct.Q4_K_S.gguf b/Alpaca-Llama-3.2-1B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..f3cd425 --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d8d4f2c270a240673ddd41467234833b2748c14456a3aa01306c772c8151f5b +size 775644064 diff --git a/Alpaca-Llama-3.2-1B-Instruct.Q5_K_M.gguf b/Alpaca-Llama-3.2-1B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..b82b7a1 --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22cf626c851f2219ed59fbcfc524da65028057a4d1cbef7051bbbc13bd9075a9 +size 911500192 diff --git a/Alpaca-Llama-3.2-1B-Instruct.Q5_K_S.gguf b/Alpaca-Llama-3.2-1B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..c470f29 --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce1f0ac4ee86077ec6319823f4b989cb2d7f81ad79eff2b2cffa7e9f1509615 +size 892560288 diff --git a/Alpaca-Llama-3.2-1B-Instruct.Q6_K.gguf b/Alpaca-Llama-3.2-1B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..7a2fba5 --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86596d1f71595d671a1821a63c088e469a83b9d3747a2a5b66a887aa88739b16 +size 1021797280 diff --git a/Alpaca-Llama-3.2-1B-Instruct.Q8_0.gguf b/Alpaca-Llama-3.2-1B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..79b4971 --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3866463d4fbd966019ca2391f36cf82068e1b15cd5ff128a903abf67bb0d87b6 +size 1321079712 diff --git a/Alpaca-Llama-3.2-1B-Instruct.f16.gguf b/Alpaca-Llama-3.2-1B-Instruct.f16.gguf new file mode 100644 index 0000000..7b353fd --- /dev/null +++ b/Alpaca-Llama-3.2-1B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e468be723829c73f3642638596c00c232a1723d11d3713f5adb5735a9bd57276 +size 2479592352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..48c15af --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: minpeter/Alpaca-Llama-3.2-1B-Instruct +datasets: +- tatsu-lab/alpaca +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +tags: +- axolotl +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/minpeter/Alpaca-Llama-3.2-1B-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/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-Llama-3.2-1B-Instruct-GGUF/resolve/main/Alpaca-Llama-3.2-1B-Instruct.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. + +