LargeWorldModel/LWM-Text-1M
291.3k
1{2 "architectures": [3 "LlamaForCausalLM"4 ],5 "bos_token_id": 1,6 "eos_token_id": 2,7 "hidden_act": "silu",8 "hidden_size": 4096,9 "initializer_range": 0.02,10 "intermediate_size": 11008,11 "max_position_embeddings": 1048576,12 "model_type": "llama",13 "num_attention_heads": 32,14 "num_hidden_layers": 32,15 "pad_token_id": 0,16 "rms_norm_eps": 1e-06,17 "rope_scaling": null,18 "rope_theta": 50000000.0,19 "tie_word_embeddings": false,20 "torch_dtype": "float16",21 "transformers_version": "4.29.2",22 "use_cache": true,23 "vocab_size": 3200024}25 