commit e9534ebdac4dc4c16921646d00c404a6f0bfa208 Author: ModelHub XC Date: Sat May 30 15:56:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5eb7c35 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-Agent007-Coder.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Agent007-Coder.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Agent007-Coder.IQ3_M.gguf b/Llama-3.2-3B-Agent007-Coder.IQ3_M.gguf new file mode 100644 index 0000000..b594cb0 --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:564f0c75ca03043d58a27614b53a6076c3986a07e2cc9d7d11056f17a3185e6e +size 1599669408 diff --git a/Llama-3.2-3B-Agent007-Coder.IQ3_S.gguf b/Llama-3.2-3B-Agent007-Coder.IQ3_S.gguf new file mode 100644 index 0000000..f3de8da --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a64ef637d2bebf18454fa8aabbcf8d550dc8f0a79fdbf50104289a128f6a3cb +size 1542849696 diff --git a/Llama-3.2-3B-Agent007-Coder.IQ3_XS.gguf b/Llama-3.2-3B-Agent007-Coder.IQ3_XS.gguf new file mode 100644 index 0000000..fce1de0 --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8752fef9391f3d69662f649ac075eef7af4489dcd9846f2f248a2b227e815c9a +size 1476789408 diff --git a/Llama-3.2-3B-Agent007-Coder.IQ4_XS.gguf b/Llama-3.2-3B-Agent007-Coder.IQ4_XS.gguf new file mode 100644 index 0000000..18df166 --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae3a252754c46c9fe7d8d99199449bed0c59368b97989397253ab92ac8cc4b0 +size 1840907424 diff --git a/Llama-3.2-3B-Agent007-Coder.Q2_K.gguf b/Llama-3.2-3B-Agent007-Coder.Q2_K.gguf new file mode 100644 index 0000000..120cf21 --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:990b61af0a7775a5113c4d4585893e9da5b946cd1dc2b52fa71d16595b91d384 +size 1363936416 diff --git a/Llama-3.2-3B-Agent007-Coder.Q3_K_L.gguf b/Llama-3.2-3B-Agent007-Coder.Q3_K_L.gguf new file mode 100644 index 0000000..a313f5a --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13aa908ae6140e89237a94677f4e2d04b458416557712f9e458f0ed203cf9928 +size 1815348384 diff --git a/Llama-3.2-3B-Agent007-Coder.Q3_K_M.gguf b/Llama-3.2-3B-Agent007-Coder.Q3_K_M.gguf new file mode 100644 index 0000000..ab62baf --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c8c8ddf90451a0add7d36214ccbfa672a7b1ea732e1d3cb73884537a8f3e52e +size 1687159968 diff --git a/Llama-3.2-3B-Agent007-Coder.Q3_K_S.gguf b/Llama-3.2-3B-Agent007-Coder.Q3_K_S.gguf new file mode 100644 index 0000000..b0e75b0 --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780385ddb7460415df1c39cad9ccccd9dfd2debad8a328f2aa37a0b5eb9b7042 +size 1542849696 diff --git a/Llama-3.2-3B-Agent007-Coder.Q4_K_M.gguf b/Llama-3.2-3B-Agent007-Coder.Q4_K_M.gguf new file mode 100644 index 0000000..4554b1b --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6602c2774860fcd88910d957850a57baf147590a6f85cb911b541e0dec4376c +size 2019378336 diff --git a/Llama-3.2-3B-Agent007-Coder.Q4_K_S.gguf b/Llama-3.2-3B-Agent007-Coder.Q4_K_S.gguf new file mode 100644 index 0000000..971d177 --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d22361695cd0985947d7e71c1d6fb9e192b6dea9ac211d2bff4872d30579ed12 +size 1928201376 diff --git a/Llama-3.2-3B-Agent007-Coder.Q5_K_M.gguf b/Llama-3.2-3B-Agent007-Coder.Q5_K_M.gguf new file mode 100644 index 0000000..fbd133c --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09fa8cfa51a2834e25205476021c1b4ec3f6c764141c965213f1489780819e9c +size 2322154656 diff --git a/Llama-3.2-3B-Agent007-Coder.Q5_K_S.gguf b/Llama-3.2-3B-Agent007-Coder.Q5_K_S.gguf new file mode 100644 index 0000000..2e48a5b --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30f35de391b8cd8b9545a52722b99dde1189455198c8cb1b3119e22c20619576 +size 2269512864 diff --git a/Llama-3.2-3B-Agent007-Coder.Q6_K.gguf b/Llama-3.2-3B-Agent007-Coder.Q6_K.gguf new file mode 100644 index 0000000..da27498 --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48f55dcd8849a305308773e5af4a43119d93be9e3b1549052f8e8c065ff82e7b +size 2643854496 diff --git a/Llama-3.2-3B-Agent007-Coder.Q8_0.gguf b/Llama-3.2-3B-Agent007-Coder.Q8_0.gguf new file mode 100644 index 0000000..aaab75c --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7908998801b61867d408ba2c469a85095dca22f70adc43b6997e17d6f442f04 +size 3421899936 diff --git a/Llama-3.2-3B-Agent007-Coder.f16.gguf b/Llama-3.2-3B-Agent007-Coder.f16.gguf new file mode 100644 index 0000000..ff37579 --- /dev/null +++ b/Llama-3.2-3B-Agent007-Coder.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:995946ad9c7924bebaea696395d15f1e9f1b4fcd864628118888b2f03014f06e +size 6433688736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fd5cdfa --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: EpistemeAI/Llama-3.2-3B-Agent007-Coder +datasets: +- sahil2801/CodeAlpaca-20k +- argilla/magpie-ultra-v0.1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/EpistemeAI/Llama-3.2-3B-Agent007-Coder + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Agent007-Coder-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-i1-GGUF +## 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-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.IQ3_XS.gguf) | IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.IQ3_S.gguf) | IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.IQ3_M.gguf) | IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-Coder-GGUF/resolve/main/Llama-3.2-3B-Agent007-Coder.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. + +