Lambent/Qwen3-4B-Base-Continued-GRPO-Style-Karcher

Update README.md

Update README.md

Patch think/endthink embeddings (fix: keep original 2-shard layout)

Patch <think>/<\/think> token embeddings with optimized vectors

Update README.md

Update README.md

Update README.md

Update README.md

model

initial commit