commit b0830275f7204e5ecdf26757bb19fee07ed8adcc Author: ModelHub XC Date: Fri Jun 19 23:58:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..35eeb24 --- /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-16bit-CodeArchitect.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-16bit-CodeArchitect.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.IQ4_XS.gguf new file mode 100644 index 0000000..82e13c0 --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a85cbdf9bde5b3f392bb1097178332472708def5cc094fd47b068453e4eb20f +size 748385728 diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q2_K.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q2_K.gguf new file mode 100644 index 0000000..24e4229 --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:545919daa15e8ed04f9f54065b1bce4b6368e60f356bf42c470ae8ae9ae03211 +size 580875712 diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_L.gguf new file mode 100644 index 0000000..13a9b58 --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7305bd3ceae07d86b24452d75f2a6a42421c130a66a08f9d979a078467e105 +size 732526016 diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_M.gguf new file mode 100644 index 0000000..f06087d --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf0ff9335cbaf24bbc682007bbd7e48ead2b107f0ab3c83948f5b046a63e899a +size 690845120 diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_S.gguf new file mode 100644 index 0000000..3151489 --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:065e1bc5d4c06a12128c51a812f5196a4d309b98e40b37ae860af80bf4157b2e +size 641693120 diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q4_K_M.gguf new file mode 100644 index 0000000..be891c6 --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69f419326e974418185cc083af49a4108a0349921ca149a38837a4cfe743c37d +size 807695808 diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q4_K_S.gguf new file mode 100644 index 0000000..079b4fa --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d03b3b9b8134c1464234f37c97cd2ada1b863667ffa3db99998d33effd7e7c27 +size 775648704 diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q5_K_M.gguf new file mode 100644 index 0000000..8870965 --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5467b391c4f0a3f91fedaf23d81e8f65a68690a1afd5fdef77ebfe35904f7dd +size 911504832 diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q5_K_S.gguf new file mode 100644 index 0000000..1144a61 --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a2c1163bccc3fa90d45a54949539fa34461de2c7f3cdad991722cbeb18b09c +size 892564928 diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q6_K.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q6_K.gguf new file mode 100644 index 0000000..54600b9 --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30b789a228a23d5b3d2357c461020bbb42e93eceb59ddf6a44d10650f44e0ac1 +size 1021801920 diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q8_0.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q8_0.gguf new file mode 100644 index 0000000..bb27110 --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f575a0c59ecc7e85ca6d018d6135f34603853f5b70c651709e6be1c2ea6dff8f +size 1321084352 diff --git a/Llama-3.2-1B-Instruct-16bit-CodeArchitect.f16.gguf b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.f16.gguf new file mode 100644 index 0000000..acce1c6 --- /dev/null +++ b/Llama-3.2-1B-Instruct-16bit-CodeArchitect.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8905b034e58d2b172163ec98a369b748656173fe06be36e814728d00bba97181 +size 2479596992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0dc37af --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: gokul-pv/Llama-3.2-1B-Instruct-16bit-CodeArchitect +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/gokul-pv/Llama-3.2-1B-Instruct-16bit-CodeArchitect + + +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-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-16bit-CodeArchitect-GGUF/resolve/main/Llama-3.2-1B-Instruct-16bit-CodeArchitect.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. + +