Text Generation
Transformers
PEFT
English
crn
cognitive-architecture
reasoning
adapter
gemma
gemma-4
CRN
cognitive-resonance-network
parameter-efficient
parameter-efficient-finetuning
hidden-state-correction
resonance-attention
episodic-memory
llm-adapter
tiny-model
efficient-inference
cpu-training
mac-m4
open-weights
experimental
research
| { | |
| "model_type": "crn", | |
| "architectures": ["PrajnaStudentMultiLayer"], | |
| "base_model": "google/gemma-4-E2B", | |
| "adapter_file": "dpo_final.pt", | |
| "memory_file": "memory_dpo_final.json", | |
| "loader": "crn_components.py", | |
| "inject_every": 8, | |
| "injection_layers": [7, 15, 23, 31], | |
| "num_injections": 4, | |
| "crn_params": 6721432, | |
| "d_model": 1536, | |
| "num_frequencies": 8, | |
| "top_k": 2, | |
| "num_skills": 32, | |
| "skill_rank": 4, | |
| "num_corrections": 8, | |
| "mem_size": 256, | |
| "mem_dim": 64, | |
| "transformers_version": "4.40.0", | |
| "library_name": "transformers", | |
| "license": "apache-2.0" | |
| } | |