jastorj/couchmind-v5.8.2_cold_start-cw-26K-16bit

LoRA-style vs Snowflake/Arctic-Text2SQL-R1-7B. 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 28 of 28 layers; norms, biases and embeddings are untouched.

Tensors changed: Norms 0/57, MLP 84/84, Attention 112/196, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse