{ "_name_or_path": "/network/eldar/llama31_8b_gsm8k/dense/sp0_2ep_lr7e-6_bs32_GradClip2_warmup20ba", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "quantization_config": { "config_groups": { "group_0": { "input_activations": null, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 128, "num_bits": 4, "observer": "mse", "observer_kwargs": {}, "strategy": "group", "symmetric": true, "type": "int" } } }, "format": "pack-quantized", "global_compression_ratio": 1.8917232374233346, "ignore": [ "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": { "format": "dense", "global_sparsity": 0.12939819101826835, "ignore": [ "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.self_attn.q_proj", "model.layers.1.self_attn.k_proj", "model.layers.1.self_attn.v_proj", "model.layers.1.self_attn.o_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.2.mlp.gate_proj", "model.layers.2.mlp.up_proj", "model.layers.2.mlp.down_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.self_attn.q_proj", "model.layers.5.self_attn.k_proj", "model.layers.5.self_attn.v_proj", "model.layers.5.self_attn.o_proj", "model.layers.5.mlp.gate_proj", "model.layers.5.mlp.up_proj", "model.layers.5.mlp.down_proj", "model.layers.6.self_attn.q_proj", "model.layers.6.self_attn.k_proj", "model.layers.6.self_attn.v_proj", "model.layers.6.self_attn.o_proj", "model.layers.6.mlp.gate_proj", "model.layers.6.mlp.up_proj", "model.layers.6.mlp.down_proj", "model.layers.7.self_attn.q_proj", "model.layers.7.self_attn.k_proj", "model.layers.7.self_attn.v_proj", "model.layers.7.self_attn.o_proj", "model.layers.7.mlp.gate_proj", "model.layers.7.mlp.up_proj", "model.layers.7.mlp.down_proj", "model.layers.8.self_attn.q_proj", "model.layers.8.self_attn.k_proj", "model.layers.8.self_attn.v_proj", "model.layers.8.self_attn.o_proj", "model.layers.8.mlp.gate_proj", "model.layers.8.mlp.up_proj", "model.layers.8.mlp.down_proj", "model.layers.9.self_attn.q_proj", "model.layers.9.self_attn.k_proj", "model.layers.9.self_attn.v_proj", "model.layers.9.self_attn.o_proj", "model.layers.9.mlp.gate_proj", "model.layers.9.mlp.up_proj", "model.layers.9.mlp.down_proj", "model.layers.10.self_attn.q_proj", "model.layers.10.self_attn.k_proj", "model.layers.10.self_attn.v_proj", "model.layers.10.self_attn.o_proj", "model.layers.10.mlp.gate_proj", "model.layers.10.mlp.up_proj", "model.layers.10.mlp.down_proj", "model.layers.11.self_attn.q_proj", "model.layers.11.self_attn.k_proj", "model.layers.11.self_attn.v_proj", "model.layers.11.self_attn.o_proj", "model.layers.11.mlp.gate_proj", "model.layers.11.mlp.up_proj", "model.layers.11.mlp.down_proj", "model.layers.12.self_attn.q_proj", "model.layers.12.self_attn.k_proj", "model.layers.12.self_attn.v_proj", "model.layers.12.self_attn.o_proj", "model.layers.12.mlp.gate_proj", "model.layers.12.mlp.up_proj", "model.layers.12.mlp.down_proj", "model.layers.13.self_attn.q_proj", "model.layers.13.self_attn.k_proj", "model.layers.13.self_attn.v_proj", "model.layers.13.self_attn.o_proj", "model.layers.13.mlp.gate_proj", "model.layers.13.mlp.up_proj", "model.layers.13.mlp.down_proj", "model.layers.14.self_attn.q_proj", "model.layers.14.self_attn.k_proj", "model.layers.14.self_attn.v_proj", "model.layers.14.self_attn.o_proj", "model.layers.14.mlp.gate_proj", "model.layers.14.mlp.up_proj", "model.layers.14.mlp.down_proj", "model.layers.15.self_attn.q_proj", "model.layers.15.self_attn.k_proj", "model.layers.15.self_attn.v_proj", "model.layers.15.self_attn.o_proj", "model.layers.15.mlp.gate_proj", "model.layers.15.mlp.up_proj", "model.layers.15.mlp.down_proj", "model.layers.16.self_attn.q_proj", "model.layers.16.self_attn.k_proj", "model.layers.16.self_attn.v_proj", "model.layers.16.self_attn.o_proj", "model.layers.16.mlp.gate_proj", "model.layers.16.mlp.up_proj", "model.layers.16.mlp.down_proj", "model.layers.17.self_attn.q_proj", "model.layers.17.self_attn.k_proj", "model.layers.17.self_attn.v_proj", "model.layers.17.self_attn.o_proj", "model.layers.17.mlp.gate_proj", "model.layers.17.mlp.up_proj", "model.layers.17.mlp.down_proj", "model.layers.18.self_attn.q_proj", "model.layers.18.self_attn.k_proj", "model.layers.18.self_attn.v_proj", "model.layers.18.self_attn.o_proj", "model.layers.18.mlp.gate_proj", "model.layers.18.mlp.up_proj", "model.layers.18.mlp.down_proj", "model.layers.19.self_attn.q_proj", "model.layers.19.self_attn.k_proj", "model.layers.19.self_attn.v_proj", "model.layers.19.self_attn.o_proj", "model.layers.19.mlp.gate_proj", "model.layers.19.mlp.up_proj", "model.layers.19.mlp.down_proj", "model.layers.20.self_attn.q_proj", "model.layers.20.self_attn.k_proj", "model.layers.20.self_attn.v_proj", "model.layers.20.self_attn.o_proj", "model.layers.20.mlp.gate_proj", "model.layers.20.mlp.up_proj", "model.layers.20.mlp.down_proj", "model.layers.21.self_attn.q_proj", "model.layers.21.self_attn.k_proj", "model.layers.21.self_attn.v_proj", "model.layers.21.self_attn.o_proj", "model.layers.21.mlp.gate_proj", "model.layers.21.mlp.up_proj", "model.layers.21.mlp.down_proj", "model.layers.22.self_attn.q_proj", "model.layers.22.self_attn.k_proj", "model.layers.22.self_attn.v_proj", "model.layers.22.self_attn.o_proj", "model.layers.22.mlp.gate_proj", "model.layers.22.mlp.up_proj", "model.layers.22.mlp.down_proj", "model.layers.23.self_attn.q_proj", "model.layers.23.self_attn.k_proj", "model.layers.23.self_attn.v_proj", "model.layers.23.self_attn.o_proj", "model.layers.23.mlp.gate_proj", "model.layers.23.mlp.up_proj", "model.layers.23.mlp.down_proj", "model.layers.24.self_attn.q_proj", "model.layers.24.self_attn.k_proj", "model.layers.24.self_attn.v_proj", "model.layers.24.self_attn.o_proj", "model.layers.24.mlp.gate_proj", "model.layers.24.mlp.up_proj", "model.layers.24.mlp.down_proj", "model.layers.25.self_attn.q_proj", "model.layers.25.self_attn.k_proj", "model.layers.25.self_attn.v_proj", "model.layers.25.self_attn.o_proj", "model.layers.25.mlp.gate_proj", "model.layers.25.mlp.up_proj", "model.layers.25.mlp.down_proj", "model.layers.26.self_attn.q_proj", "model.layers.26.self_attn.k_proj", "model.layers.26.self_attn.v_proj", "model.layers.26.self_attn.o_proj", "model.layers.26.mlp.gate_proj", "model.layers.26.mlp.up_proj", "model.layers.26.mlp.down_proj", "model.layers.27.self_attn.q_proj", "model.layers.27.self_attn.k_proj", "model.layers.27.self_attn.v_proj", "model.layers.27.self_attn.o_proj", "model.layers.27.mlp.gate_proj", "model.layers.27.mlp.up_proj", "model.layers.27.mlp.down_proj", "model.layers.28.self_attn.q_proj", "model.layers.28.self_attn.k_proj", "model.layers.28.self_attn.v_proj", "model.layers.28.self_attn.o_proj", "model.layers.28.mlp.gate_proj", "model.layers.28.mlp.up_proj", "model.layers.28.mlp.down_proj", "model.layers.29.self_attn.q_proj", "model.layers.29.self_attn.k_proj", "model.layers.29.self_attn.v_proj", "model.layers.29.self_attn.o_proj", "model.layers.29.mlp.gate_proj", "model.layers.29.mlp.up_proj", "model.layers.29.mlp.down_proj", "model.layers.30.self_attn.q_proj", "model.layers.30.self_attn.k_proj", "model.layers.30.self_attn.v_proj", "model.layers.30.self_attn.o_proj", "model.layers.30.mlp.gate_proj", "model.layers.30.mlp.up_proj", "model.layers.30.mlp.down_proj", "model.layers.31.self_attn.q_proj", "model.layers.31.self_attn.k_proj", "model.layers.31.self_attn.v_proj", "model.layers.31.self_attn.o_proj", "model.layers.31.mlp.gate_proj", "model.layers.31.mlp.up_proj", "model.layers.31.mlp.down_proj", "lm_head" ], "registry_requires_subclass": false, "sparsity_structure": "unstructured", "targets": [ "model.layers.0.self_attn.q_proj", "model.layers.0.self_attn.k_proj" ] } }, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.45.2", "use_cache": true, "vocab_size": 128256 }