| { | |
| "_name_or_path": "relaxml/Llama-1-30b-hf", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 6656, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 17920, | |
| "max_position_embeddings": 2048, | |
| "model_type": "llama", | |
| "num_attention_heads": 52, | |
| "num_hidden_layers": 60, | |
| "num_key_value_heads": 52, | |
| "pretraining_tp": 1, | |
| "quip_params": { | |
| "codebook": "E8P12", | |
| "codebook_version": 1, | |
| "codesz": 8, | |
| "fused": true, | |
| "idx_dtype": "torch.int64", | |
| "lora_rank": 0, | |
| "model_version": 1, | |
| "outlier_channel_split": false, | |
| "packsz": 4, | |
| "rescale_WH": false, | |
| "resid_scale_override": -1 | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.36.2", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |