Codemaster67/Unichem_chebi_10M_tokens

Adapter vs allenai/OLMo-1B-hf. Codemaster67/Unichem_chebi_10M_tokens is a LoRA adapter, not full weights: rank 64, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 16 layers (112 adapted matrices). It modifies allenai/OLMo-1B-hf at load time.

On the Hub · Downloads on Model Pulse