HyperAiCorp/Nova-1.1-0.8B
LoRA-style vs HyperAiCorp/Nova-1-0.8B. 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 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/129, Attention 24/216, MLP 72/124
2 derivatives checked
- mradermacher/Nova-1.1-0.8B-i1-GGUF: Quantization
- mradermacher/Nova-1.1-0.8B-GGUF: Same weights, converted