| { |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "dtype": "float16", |
| "eos_token_id": 2, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 512, |
| "initializer_range": 0.02, |
| "intermediate_size": 1408, |
| "max_position_embeddings": 32768, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 8, |
| "num_key_value_heads": 2, |
| "pad_token_id": null, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "rope_theta": 1000000.0, |
| "rope_type": "default" |
| }, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.3.0", |
| "use_cache": true, |
| "vocab_size": 6400 |
| } |
|
|
