Josephgflowers/TinyLlama-R1-LIMO
LoRA-style vs Josephgflowers/Tinyllama-STEM-Cinder-Agent-v1. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 22 of 22 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/45, MLP 66/66, Attention 88/88
2 derivatives checked
- mradermacher/TinyLlama-R1-LIMO-i1-GGUF: Quantization
- mradermacher/TinyLlama-R1-LIMO-GGUF: Same weights, converted