{ "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151646, "torch_dtype": "bfloat16", "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 27648, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 131072, "max_window_layers": 64, "model_type": "qwen2", "num_attention_heads": 40, "num_hidden_layers": 64, "num_key_value_heads": 8, "pad_token_id": 151654, "quantization_config": { "bnb_4bit_compute_dtype": "bfloat16", "bnb_4bit_quant_type": "nf4", "bnb_4bit_use_double_quant": true, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": [ "model.layers.0.self_attn.q_proj", "model.layers.0.self_attn.k_proj", "model.layers.0.self_attn.v_proj", "model.layers.0.self_attn.o_proj", "model.layers.0.mlp.gate_proj", "model.layers.0.mlp.up_proj", "model.layers.0.mlp.down_proj", "model.layers.1.mlp.gate_proj", "model.layers.1.mlp.up_proj", "model.layers.1.mlp.down_proj", "model.layers.2.self_attn.q_proj", "model.layers.2.self_attn.k_proj", "model.layers.2.self_attn.v_proj", "model.layers.2.self_attn.o_proj", "model.layers.3.self_attn.q_proj", "model.layers.3.self_attn.k_proj", "model.layers.3.self_attn.v_proj", "model.layers.3.self_attn.o_proj", "model.layers.3.mlp.gate_proj", "model.layers.3.mlp.up_proj", "model.layers.3.mlp.down_proj", "model.layers.4.self_attn.q_proj", "model.layers.4.self_attn.k_proj", "model.layers.4.self_attn.v_proj", "model.layers.4.self_attn.o_proj", "model.layers.4.mlp.gate_proj", "model.layers.4.mlp.up_proj", "model.layers.4.mlp.down_proj", "model.layers.5.mlp.gate_proj", "model.layers.5.mlp.up_proj", "model.layers.5.mlp.down_proj", "model.layers.6.mlp.gate_proj", "model.layers.6.mlp.up_proj", "model.layers.6.mlp.down_proj", "model.layers.38.mlp.gate_proj", "model.layers.38.mlp.up_proj", "model.layers.38.mlp.down_proj", "model.layers.39.self_attn.o_proj", "model.layers.39.mlp.gate_proj", "model.layers.39.mlp.up_proj", "model.layers.39.mlp.down_proj", "model.layers.40.self_attn.o_proj", "model.layers.43.self_attn.o_proj", "model.layers.43.mlp.gate_proj", "model.layers.43.mlp.up_proj", "model.layers.43.mlp.down_proj", "model.layers.47.mlp.gate_proj", "model.layers.47.mlp.up_proj", "model.layers.47.mlp.down_proj", "model.layers.48.mlp.gate_proj", "model.layers.48.mlp.up_proj", "model.layers.48.mlp.down_proj", "model.layers.49.mlp.gate_proj", "model.layers.49.mlp.up_proj", "model.layers.49.mlp.down_proj", "model.layers.50.mlp.gate_proj", "model.layers.50.mlp.up_proj", "model.layers.50.mlp.down_proj", "model.layers.51.mlp.gate_proj", "model.layers.51.mlp.up_proj", "model.layers.51.mlp.down_proj", "model.layers.52.mlp.gate_proj", "model.layers.52.mlp.up_proj", "model.layers.52.mlp.down_proj", "model.layers.53.mlp.gate_proj", "model.layers.53.mlp.up_proj", "model.layers.53.mlp.down_proj", "model.layers.54.mlp.gate_proj", "model.layers.54.mlp.up_proj", "model.layers.54.mlp.down_proj", "model.layers.55.mlp.gate_proj", "model.layers.55.mlp.up_proj", "model.layers.55.mlp.down_proj", "model.layers.56.mlp.gate_proj", "model.layers.56.mlp.up_proj", "model.layers.56.mlp.down_proj", "model.layers.57.mlp.gate_proj", "model.layers.57.mlp.up_proj", "model.layers.57.mlp.down_proj", "model.layers.58.mlp.gate_proj", "model.layers.58.mlp.up_proj", "model.layers.58.mlp.down_proj", "model.layers.59.mlp.gate_proj", "model.layers.59.mlp.up_proj", "model.layers.59.mlp.down_proj", "model.layers.60.mlp.gate_proj", "model.layers.60.mlp.up_proj", "model.layers.60.mlp.down_proj", "model.layers.61.mlp.gate_proj", "model.layers.61.mlp.up_proj", "model.layers.61.mlp.down_proj", "model.layers.62.mlp.gate_proj", "model.layers.62.mlp.up_proj", "model.layers.62.mlp.down_proj", "lm_head" ], "llm_int8_threshold": 6.0, "load_in_4bit": true, "load_in_8bit": false, "quant_method": "bitsandbytes" }, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "transformers_version": "4.57.6", "unsloth_fixed": true, "unsloth_version": "2026.1.4", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064 }