commit 4bac0496a0f4ddbcd7908c8a85aea36364e7b28b Author: ModelHub XC Date: Wed Sep 23 17:07:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1803732 --- /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-gsm8k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-gsm8k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-gsm8k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-gsm8k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-gsm8k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-gsm8k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-gsm8k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-gsm8k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-gsm8k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-gsm8k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-gsm8k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-gsm8k.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-gsm8k.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-gsm8k.IQ4_XS.gguf new file mode 100644 index 0000000..19cdddb --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123fca4dcd85ac3141703b1f82c5bf616bba1a0bb43bafd4cc8eb5ee7727dc96 +size 748382176 diff --git a/Llama-3.2-1B-Instruct-gsm8k.Q2_K.gguf b/Llama-3.2-1B-Instruct-gsm8k.Q2_K.gguf new file mode 100644 index 0000000..83a6ac1 --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50f73001db9e66101b325a5111b031a3a36d4fcbc4b4d22b9bb5585b81087fbf +size 580872160 diff --git a/Llama-3.2-1B-Instruct-gsm8k.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-gsm8k.Q3_K_L.gguf new file mode 100644 index 0000000..2b62e5a --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f2a7882b292ef57a7419e823ae4e94829b2d1e102e9a4f6ac31b1190b8a18c +size 732522464 diff --git a/Llama-3.2-1B-Instruct-gsm8k.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-gsm8k.Q3_K_M.gguf new file mode 100644 index 0000000..015b0af --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf499c20e99dd1ffc5401b756da81f3e4fd1d5a3bca4168e7d418ef49ac45c6 +size 690841568 diff --git a/Llama-3.2-1B-Instruct-gsm8k.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-gsm8k.Q3_K_S.gguf new file mode 100644 index 0000000..fdc5195 --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cddd832f651d765171c0824c6c73b7dc00298a5460fd46d47edfdb5f7e10939e +size 641689568 diff --git a/Llama-3.2-1B-Instruct-gsm8k.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-gsm8k.Q4_K_M.gguf new file mode 100644 index 0000000..63cb8d5 --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d094c1190c8c95131717d631e65e5f5a854ec11e4cc9b003b51f98d606638404 +size 807692256 diff --git a/Llama-3.2-1B-Instruct-gsm8k.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-gsm8k.Q4_K_S.gguf new file mode 100644 index 0000000..1260411 --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11c9c852942d2a4423bb8edc0c47516d3ae5d1ff9ad81baa9a517902c481bb71 +size 775645152 diff --git a/Llama-3.2-1B-Instruct-gsm8k.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-gsm8k.Q5_K_M.gguf new file mode 100644 index 0000000..223bb36 --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04de460537e6786663a6cdfbd0c4cfaa6c20619a91a718792c63a71446f499ee +size 911501280 diff --git a/Llama-3.2-1B-Instruct-gsm8k.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-gsm8k.Q5_K_S.gguf new file mode 100644 index 0000000..38094e1 --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5dd215eea884369e8013547b3887ea254991fe83a8ffdb7237a297c6cd634ef +size 892561376 diff --git a/Llama-3.2-1B-Instruct-gsm8k.Q6_K.gguf b/Llama-3.2-1B-Instruct-gsm8k.Q6_K.gguf new file mode 100644 index 0000000..4e7aa1d --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f84c1468b62df5d2b306ed952b17b3a6ebca3b2c3b215a7ea62caae001cf679e +size 1021798368 diff --git a/Llama-3.2-1B-Instruct-gsm8k.Q8_0.gguf b/Llama-3.2-1B-Instruct-gsm8k.Q8_0.gguf new file mode 100644 index 0000000..668ab86 --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d121d396435e717e68b5f026f8528a171f2be8e0b25a9f1881f466e2f3244c1 +size 1321081280 diff --git a/Llama-3.2-1B-Instruct-gsm8k.f16.gguf b/Llama-3.2-1B-Instruct-gsm8k.f16.gguf new file mode 100644 index 0000000..0226c44 --- /dev/null +++ b/Llama-3.2-1B-Instruct-gsm8k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5140f90c7521b84f865ced377504d8d62efd14c69d222c0f862fc5c10fef3e3f +size 2479595840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4588f78 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: ank028/Llama-3.2-1B-Instruct-gsm8k +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-gsm8k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-Instruct-gsm8k-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-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-gsm8k-GGUF/resolve/main/Llama-3.2-1B-Instruct-gsm8k.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. + +