v4.2: update model card with balanced eval scores (75% overall, std=8.4)

Upload model.safetensors with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload tokenizer.json with huggingface_hub

Upload generation_config.json with huggingface_hub

Upload config.json with huggingface_hub

Upload README.md with huggingface_hub

docs: honest CUDA limitations

fix: auto-download instructions in quick start

docs: fix stale question/category counts

docs: add solo maintainer disclaimer

fix: remove stale sampling params from generation_config (suppresses warning)

weights: PEFT-merged with stale tool name fixes (golden model)

Remove old shard model.safetensors.index.json

Remove old shard model-00004-of-00004.safetensors

Remove old shard model-00003-of-00004.safetensors

Remove old shard model-00002-of-00004.safetensors

Remove old shard model-00001-of-00004.safetensors

docs: remove research planning claims

docs: update benchmark scores (74% overall, agentic_tool_use 62->81%)

docs: add real example outputs from E2E testing

docs: use tokenizer tools= param for tool calling example

Delete convergent-banner.png with huggingface_hub

Upload folder using huggingface_hub

Upload README.md with huggingface_hub

Upload convergent-banner.jpg with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload convergent-banner.png with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

initial commit