| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": [ | |
| 1, | |
| 130073 | |
| ], | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 42, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 1, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 5000000, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.14.1", | |
| "use_cache": true, | |
| "vocab_size": 130560, | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": { | |
| "dynamic": false, | |
| "num_bits": 8, | |
| "type": "float" | |
| }, | |
| "weights": { | |
| "dynamic": false, | |
| "num_bits": 8, | |
| "type": "float" | |
| }, | |
| "targets": [ | |
| "Linear" | |
| ] | |
| } | |
| }, | |
| "ignore": [ | |
| "lm_head", | |
| "model.embed_tokens" | |
| ], | |
| "quant_algo": "FP8", | |
| "producer": { | |
| "name": "modelopt", | |
| "version": "0.47.0" | |
| }, | |
| "quant_method": "modelopt" | |
| } | |
| } |