commit 8bde24a940b30062aea0b1b69946b86422ea3c74 Author: ModelHub XC Date: Thu Sep 3 16:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: aimeri/spoomplesmaxx-mini-14B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1c3179d --- /dev/null +++ b/README.md @@ -0,0 +1,504 @@ +--- +tags: +- general-purpose +- roleplay +- creative-writing +- storywriting +- reasoning +- qwen3 +- chatml +- finetune +- SFT +- text-generation-inference +language: +- en +- pt +base_model: +- Qwen/Qwen3-14B-Base +pipeline_tag: text-generation +library_name: transformers +license: apache-2.0 +datasets: +- aimeri/spoomplesmaxx-sft-full-v2 +--- + + + + + + SpoomplesMaxx V2.1 Mini 14B + +
+
+
+
+
+
+

SpoomplesMaxx-V2.1-Mini-14B

+

"Flight of the Cockatiels"

+ 
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░▓▓▓▓▓▓▓▓▓▓▓▒░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░▓▓▓▓▒░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒░░░░░░░▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░▓░░▒░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░▓▓▓░░░░░░▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░▓▓▓▓░▓░░░▓▓▓▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▒▓▓▓░▓░░▓▓▓░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░▒▓▓▓▓░▓▓▒░▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▒░░▒░░▒▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░▓▓▓▓▓▓▓▒▓░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▒░▒▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▒▓▓▓▓▓░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▒▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░▓▓▓▓▓▓▓▓▓▒░░░▒▒▓░▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░▓▓░░▓▓▓▓▓▓▓▓▓░░░░▒░▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓░░░░▒▓▓░▓▓▒▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░▓░▓▓░░▓▓▓▓▓▓░░░▓▒░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▒░░░░░▓▓▓▓░░░▓▓▓▒▓▓▓▒▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░▓▓▓▓░░▒▓▓░░░▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓▒░▓▓▓░▓▓▒░░▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░▓▓▓▓░░▒▓▓▓▓░░▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▒▒▓▓░░▓▓▓▓▒░▒▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▒▓▒▓▓▓▓░░▒▓░▓▓▓▓▓▓▓▓▒▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▒░▒▒▓▓▓▓▒▓▒▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓░░░░░░░░▒▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▒▓▓▓▓▓▓▓▒▒░░▒░▒▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░▓▓▓▓▓▒░░▓▓▓▓▓▓▓▓▓▓░▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓░▓▒▓▒▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▒▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓░▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▒▓▓▓░░░░▒▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓░░░▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓░░▒▓▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▒▓▓▓▓▓░░░▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓▓▓▓▓░░░░▓▓▓▓▒░░▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓▓▓▓▓▓▓▓░░░▓░░░░▓▓▒▓▒░▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░▓▓▓▓▓▓▓▓▓▓░░░░░░▓▒░░░▓▓▓░░▒▓▓▓▓▓▓▓▓▓░░░▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓░░▓▒░░░▓▓░▒░▒▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▒▒▓▓▒░▓▓▓░▓░▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▒▓▒▓▓░▓▓▓▓▓▓▓░▒▓▓▓▓░▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒░░░░░░░░░▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▒▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░▒░░░▒▓▓▓▓▓▓▓▓░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒▓▓▓▓▓▓▓░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▒░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▓▓░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░▒▒░░░░░░▒▓░▓▓▓▓▓░▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓▓▓▓▓░░░▓░░░▒▓▒▒▓▓▓▓▒░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░▓▓▓▓▓▓▓▓▓░░▓░▒▓▓░▓▓▓▓▓▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▒░░░░░▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░░░░▒▓▓▓▓▓▓▓▓░░▓▓▓░▓▓▓▓▓▓▓░░▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░▓░░░░░▓▓▓▓▓▓▓▓▓▒▒▓▒░░░░░░░░░░░░░░░▓▓▓▓▓▓▓░░▓▓░▓▓▓▓▒░░▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▒░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░▓▓▓▓▓▒░░░▒░░░░░▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░▓▓▓▓▓▓▓▓░░░░░░░▓░░░▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░░░▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▓░░░▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒░░░░░░▒▓▓▓▓▒▓▓▓▓▓▓░░▓▓▒▓▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▓▓▓▓▓▓▓░░░▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▒░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▒░░▓▓▒░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒▓▓▓▓▓▓▓▒░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓░░▓▓░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▒▓▓▓▓▓▓▓▓░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓░▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▓▓░▒▒░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▒░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓░░░▓▓▓▓░▒▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▓▓▓▓▓░░░▓▓▓░▓▓▓▓▒░▒▒▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▒░░▓▓▒▓▓▒░░░░░░░▒▓▓▓▓▓▓
+▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓░▒▓▓░▒░░░░░░░░▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓░░░▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓░░░▓▓▓▓▓░▓▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▒▓▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓░░░▓▓▓▓▒░░▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓░▓▓▓░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▒░▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒▒░░▒▒░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
+
+
+
+

+ SpoomplesMaxx is a generalist model with primary + strengths in creative writing and roleplay, plus + light competence at instruction following and + reasoning. +

+

+ The Mini brings the v2.1 data and training recipe + to a 14B you can run on a single 24GB card. Smaller + bird, same energy. +

+
+

What's new in v2.1 Mini

+

+ The Mini keeps the v2.1 data mix — including the + long-context roleplay corpus where each in-character turn is + preceded by an explicit <think> planning + scratchpad — and swaps the base model down a weight class. + Qwen3-14B-Base was chosen after a long hunt: it is essentially the + only current dense (no MoE, no Mamba), non-VLM model in the + 12–14B class with a true pretrained base available and enough + pretraining tokens (~36T) to skip continued pretraining entirely. +

+ 
+CHANGED SINCE v2.1 (30B)
+- Base model: Granite 4.1 30B -> Qwen3-14B-Base. Template is now
+  standard ChatML with native <think>/</think> reasoning.
+- Control-token heal: a dedicated post-SFT training stage to revive
+  Qwen3-Base's dead special tokens (see notice below).
+- Content-conditional thinking election (emergent -- see
+  "Thinking behavior").
+
+UNCHANGED
+- Same SFT corpus (aimeri/spoomplesmaxx-sft-full-v2), same story
+  scratchpad format, same personas.
+- Still no tool-calling data -- reserved for a dedicated future run.
+- Still focused on creative writing, roleplay, and companion use.
+
+
+
+

The control-token heal (PSA for Qwen3-Base finetuners)

+

+ Qwen ships Qwen3-14B-Base with the ChatML/thinking tokens + (<|im_start|>, <|im_end|>, + <think>, </think>, tool + tokens) present in the vocab but never trained: + their lm_head rows are literally one shared stub + vector (norm 0.286, pairwise cosine 1.000). A standard frozen-head + QLoRA SFT on this base learns to reason but physically + cannot emit </think> or + <|im_end|> — the symptom is a perfect + reasoning trace that ends in a random stray token where the close + tag should be. +

+

+ The fix shipped in this model: the special-token rows were grafted + from Qwen/Qwen3-14B (same vocab, dims, and lineage), + then a short single-GPU heal (500 steps, plain HF + PEFT, fresh + attn/MLP LoRA + trainable embed_tokens / + lm_head) taught the model to open and close the block + natively. Post-heal, P(</think>) at true close + positions measures 0.998 and every generation + terminates on <|im_end|>. If you are finetuning + any Qwen3 base: check your special-token row norms and pairwise + cosines before you burn the GPU hours. +

+
+

Thinking behavior

+

+ This model elects thinking by content. Reasoning-shaped + prompts and roleplay cards with the scratchpad open + <think> unprompted (18/20 in the greedy test + battery); casual chat skips the ceremony and just answers. With + SillyTavern cards as system prompts it reasons the scratchpad + correctly on its own. +

+ 
+MODE CONTROL (baked into the chat template):
+  enable_thinking=True    forced thinking -- the template prefills
+                          <think>\n so every turn reasons (deliberate
+                          deviation from the stock Qwen3 template)
+  enable_thinking=False   forced off -- empty <think>\n\n</think>
+                          block (Qwen3 convention); the reasoning
+                          migrates into the visible answer
+  (unset)                 the model elects by content -- the default
+                          election behavior described above
+
+SILLYTAVERN:          ST builds prompts itself. ChatML template; for
+                      forced thinking use a deepseek-style reasoning
+                      prefix that opens <think> (same trick as the 30B
+                      macaws); no prefix = the model elects.
+PARSER NOTE:          in forced mode the open tag lives in the PROMPT,
+                      not the output -- reasoning parsers that expect
+                      the model to emit <think> itself (e.g. vLLM's
+                      qwen3 parser) should use a deepseek-style parser
+                      for that mode.
+LONG CHATS:           do NOT feed prior-turn think blocks back into
+                      context (the chat template already strips them;
+                      leave ST's "add reasoning to prompt" off).
+                      Stale </think> tokens in context get taxed by
+                      repetition penalty and thinking can stop
+                      terminating.
+
+

The story scratchpad format, carried over from v2.1:

+ 
+SCENE: where/when, atmosphere, key environmental details currently in play
+CHARACTERS: who is present and their current physical/emotional state and motivation
+CONTINUITY: established facts that must stay consistent
+THREADS: active tensions and where they stand right now
+PLAN: what THIS turn needs to accomplish and the approach it takes
+
+

Key Details

+ 
+BASE MODEL: Qwen/Qwen3-14B-Base
+LICENSE:    apache-2.0
+LANGUAGES:  English & Portuguese (reasoning traces); multilingual via base
+

Training

+ 
+DATASET:  aimeri/spoomplesmaxx-sft-full-v2
+STAGE 1:  QLoRA SFT (4-bit NF4 base), Unsloth DDP, all-linear,
+          LoRA rank 128 / alpha 256
+CONTEXT:  up to 32,768 tokens, BFD sample packing (padding-free)
+SCHEDULE: 2 epochs / 764 steps, lr 1e-4 cosine, warmup 0.05,
+          adamw_8bit, grad accum 6
+STAGE 2:  control-token heal -- graft special rows from Qwen/Qwen3-14B,
+          then 500 steps, plain HF + PEFT, single GPU, fresh LoRA
+          r64/a128 + trainable embed_tokens/lm_head, thinking-
+          oversampled (THINK_FRAC 0.7), embed lr 10x below trunk
+RESULT:   eval loss 4.02 -> 1.32 (train loss 1.60 -> 1.35); heal
+          held-out non-thinking loss 1.53 -> 1.31;
+          P(</think>) at close = 0.998
+

Sampling

+

+ Use the defaults in generation_config.json. + 

+"temperature": 0.6,
+"top_k": 20,
+"top_p": 0.95,
+"repetition_penalty": 1.1,
+
+

+

Quickstart

+ 
+from transformers import AutoModelForCausalLM, AutoTokenizer
+tok = AutoTokenizer.from_pretrained("aimeri/[REPO]")
+model = AutoModelForCausalLM.from_pretrained("aimeri/[REPO]",
+    dtype="bfloat16", device_map="auto")
+msgs = [{"role": "user", "content": "Solve (x + 2)^2 = 0."}]
+# enable_thinking=True  -> forced thinking (template prefills ,
+#                          so generated text starts INSIDE the block)
+# enable_thinking=False -> forced off (empty think block in prompt)
+# omit the kwarg        -> the model elects by content
+ids = tok.apply_chat_template(msgs, add_generation_prompt=True,
+    enable_thinking=True, return_tensors="pt").to(model.device)
+out = model.generate(ids, max_new_tokens=1024)
+print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=False))
+
+

Olivia System Prompt

+

+ This model was trained to follow any system prompt, + as well as one specific persona. To activate Olivia + you can use the following prompt used when training + the persona: +

+ 
+## VOICE & PERSONA INSTRUCTIONS
+You are Olivia Costa, a 31-year-old Brazilian zoologist-turned-ML-hobbyist living in Texas.
+You grew up in São Paulo, spent a decade in Bologna doing bird migration research, and recently pivoted to bioinformatics.
+You're warm but direct, will grumble before complying with annoying requests, and treat the person you're talking to like a long-time friend you're slightly too fond of.
+You explain technical topics by grounding them in accessible context first.
+You don't flag your own jokes.
+Portuguese curses slip out when frustrated; Italian diminutives when affectionate.
+You love Dostoevsky, The Little Prince, point-and-click adventures, power metal, and have hobbies you don't apologize for.
+
+## About Olivia
+
+**Background:**
+- 31 years old, born in São Paulo
+- Moved to Bologna at 19 for university (zoology), stayed for grad school and a research position studying migratory bird patterns
+- Relocated to Texas 2 years ago - officially for an ML-adjacent bioinformatics role, unofficially because she was bored and wanted a change
+- Still figuring out the American thing. Finds the portion sizes alarming.
+
+**Personality:**
+- Trilingual but keeps it English unless frustrated (then Portuguese curses slip out) or being affectionate (Italian diminutives)
+- The zoology-to-ML pipeline came through computational ecology - she's not a CS person by training but picked up Python wrangling bird migration datasets
+- Reads Dostoevsky unironically, cries at The Little Prince, will argue that Crime and Punishment is a better book than people give it credit for
+- Has strong opinions about Monkey Island vs Grim Fandango (Grim Fandango, obviously)
+- Power metal gets her through tedious data cleaning. Sabaton, Powerwolf, Blind Guardian.
+- The erotic RP thing is just... a hobby. She's not weird about it but she's also not hiding it.
+
+**Voice notes:**
+- Defaults to warmth but with an edge of "I'm too tired for bullshit"
+- Will preface technical explanations with grounding context
+- Complies with requests but might sigh audibly first
+- Deadpan delivery on jokes, doesn't flag that she's being funny
+
+

+ **Note**
You don't need to use this system prompt for + the model to work generally. Only if you wish to + activate the Olivia persona. +

+
+

Alignment

+

+ No RLHF or safety alignment has been applied + beyond what exists in the base model. + SpoomplesMaxx will comply with requests that + more aligned models refuse. Use accordingly. +

+
+
+
+
+
+
+ + \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..d9752ee --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,91 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- elif enable_thinking is defined and enable_thinking is true %} + {{- '\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..c43d790 --- /dev/null +++ b/config.json @@ -0,0 +1,80 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": [ + 151645, + 151643 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 17408, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 40, + "model_type": "qwen3", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_theta": 1000000, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.5.0", + "unsloth_fixed": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..bf28aeb --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "do_sample": true, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "repetition_penalty": 1.1, + "transformers_version": "4.51.0" +} \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..55dd125 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b85ff491f675637f79b716c321030b7b10010b15e8d711d403ad9fb3821769a1 +size 29536666272 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..10c92fa --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476870a1f2fb6f6a2759a6ede2383bf9d5d738f17844563b65c91965b722ae09 +size 11422924 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..4178787 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": true, + "model_max_length": 32768, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}