{ "_name_or_path": "tangledgroup/tangled-llama-108m-32k-base-v0.1", "architectures": [ "LlamaForCausalLM" ], "bos_token_id": 1, "eos_token_id": 2, "hidden_size": 512, "intermediate_size": 2048, "max_position_embeddings": 32768, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 20, "num_key_value_heads": 4, "rms_norm_eps": 1e-05, "rope_scaling": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.44.2", "use_cache": true, "vocab_size": 32768 }