T145/KRONOS-8B-V1-P1
LoRA-style vs unsloth/Meta-Llama-3.1-8B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 64/128, lm_head 0/1
5 derivatives checked
- mradermacher/KRONOS-8B-V1-P1-GGUF: Same weights, converted
- T145/KRONOS-8B-V2: Full fine-tune
- T145/KRONOS-8B-V3: Full fine-tune
- T145/KRONOS-8B-V4: LoRA-style
- T145/KRONOS-8B-V9: Partial fine-tune