Josephgflowers/Tinyllama-STEM-Cinder-Agent-v1
Full fine-tune vs Josephgflowers/TinyLlama-Cinder-Agent-v1. Fine-tune: 100% of the weights changed, across 22 of 22 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 45/45, MLP 66/66, Attention 88/88
3 derivatives checked
- mradermacher/Tinyllama-STEM-Cinder-Agent-v1-GGUF: Same weights, converted
- Josephgflowers/Tinyllama-r1: LoRA-style
- Josephgflowers/TinyLlama-R1-LIMO: LoRA-style