| { | |
| "RoPE": { | |
| "lask_k_rope_dim": 0, | |
| "n_gqa_group": 1, | |
| "partial_rope_version": 4, | |
| "qk_tensor_path": "../utils/qk_tensor_7B.pth", | |
| "top_k_rope_dim": 8, | |
| "uniform_start_point": 0, | |
| "uniform_step": 1 | |
| }, | |
| "SVD": { | |
| "low_rank": 64, | |
| "method": 7 | |
| }, | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.3", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |