| { | |
| "_name_or_path": "autodl-tmp/llama/ptm/outputs/ckpt/ptm_tiny_llm_800m_epoch2/checkpoint-170000", | |
| "architectures": [ | |
| "TinyllmForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_tinyllm.TinyllmConfig", | |
| "AutoModelForCausalLM": "modeling_tinyllm.TinyllmForCausalLM" | |
| }, | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2816, | |
| "max_position_embeddings": 1024, | |
| "model_type": "tinyllm", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.38.2", | |
| "use_cache": false, | |
| "vocab_size": 64799 | |
| } | |