| { |
| "architectures": [ |
| "DharaARForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_dhara_ar.DharaARConfig", |
| "AutoModelForCausalLM": "modeling_dhara_ar.DharaARForCausalLM" |
| }, |
| "canon_activation": false, |
| "canon_bias": false, |
| "canon_kernel": 4, |
| "canon_residual": true, |
| "canon_set": "ABCD", |
| "dtype": "bfloat16", |
| "eos_token_id": 49154, |
| "hidden_act": "silu", |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 2176, |
| "logit_softcap": 30.0, |
| "mask_token_id": 49152, |
| "max_position_embeddings": 32768, |
| "mlp_bias": false, |
| "model_type": "dhara_ar", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 4, |
| "quantization": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine", |
| "model.layers.1.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.1.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.1.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.3.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.3.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.3.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.4.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.4.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.4.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.6.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.6.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.6.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.7.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.7.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.7.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.9.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.9.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.9.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.11.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.11.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.11.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.13.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.13.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.13.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.16.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.16.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.16.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.17.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.17.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.17.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.18.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.18.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.18.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.19.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.19.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.19.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.20.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.20.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.20.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.21.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.21.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.21.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.22.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.22.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.22.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.22.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.23.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.23.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.23.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.23.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.24.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.24.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.24.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.25.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.25.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.25.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.25.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.26.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.26.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.26.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.26.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.26.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.27.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.27.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.27.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.27.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.28.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.28.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.28.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.28.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.28.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.29.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.29.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.29.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.29.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.30.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.30.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.30.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| } |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine", |
| "model.layers.1.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.1.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.1.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.3.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.3.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.3.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.4.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.4.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.4.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.6.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.6.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.6.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.7.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.7.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.7.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.9.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.9.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.9.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.11.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.11.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.11.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.13.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.13.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.13.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.16.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.16.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.16.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.17.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.17.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.17.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.18.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.18.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.18.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.19.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.19.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.19.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.20.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.20.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.20.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.21.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.21.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.21.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.22.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.22.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.22.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.22.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.23.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.23.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.23.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.23.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.24.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.24.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.24.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.25.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.25.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.25.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.25.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.26.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.26.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.26.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.26.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.26.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.27.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.27.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.27.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.27.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.28.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.28.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.28.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.28.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.28.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.29.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.29.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.29.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.29.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.30.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.30.mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.30.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| } |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": null, |
| "rope_theta": 8000000.0, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.8.1", |
| "use_logit_softcap": true, |
| "use_qk_norm": true, |
| "vocab_size": 49155 |
| } |
