alexliap/KaLM-Embedding-Gemma3-12B-CausalLM-FP8-DYNAMIC Sentence Similarity • 12B • Updated 17 days ago • 24
alexliap/KaLM-Embedding-Gemma3-12B-CausalLM-FP8-DYNAMIC Sentence Similarity • 12B • Updated 17 days ago • 24
🤏 Smol-Data Collection Tried and tested mixes for strong pretraining. Inspired by https://huggingface.co/blog/codelion/optimal-dataset-mixing • 14 items • Updated 4 days ago • 11