AetherResearch/Cerebrum-1.0-7b
LoRA-style vs mistralai/Mistral-7B-v0.1. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 64/96, Attention 128/128, lm_head 0/1
5 derivatives checked
- mradermacher/Cerebrum-1.0-7b-i1-GGUF: Quantization
- featherless-ai-quants/AetherResearch-Cerebrum-1.0-7b-GGUF: Quantization
- mradermacher/Cerebrum-1.0-7b-GGUF: Same weights, converted
- ABX-AI/Cerebral-Infinity-7B: Full fine-tune
- Kukedlc/SuperMente-7B: Full fine-tune