| { | |
| "_mlp_class": "LLaMAMLP", | |
| "_norm_class": "RMSNorm", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "bias": false, | |
| "block_size": 2048, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "gelu_approximate": "none", | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6912, | |
| "lm_head_bias": false, | |
| "max_position_embeddings": 2048, | |
| "model_type": "llama", | |
| "n_embd": 2560, | |
| "n_head": 16, | |
| "n_layer": 32, | |
| "n_query_groups": 16, | |
| "name": "huggy_llama_3b", | |
| "norm_eps": 1e-06, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "org": "meta", | |
| "pad_token_id": 0, | |
| "padded_vocab_size": 32000, | |
| "padding_multiple": 64, | |
| "parallel_residual": false, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_base": 10000, | |
| "rope_condense_ratio": 1, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "rotary_percentage": 1.0, | |
| "shared_attention_norm": false, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.31.0", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |