| { | |
| "_name_or_path": "bagel-dpo-20b-v04", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attn_implementation": "eager", | |
| "bias": false, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 6144, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 16384, | |
| "max_position_embeddings": 32768, | |
| "model_type": "llama", | |
| "num_attention_heads": 48, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 2, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.37.1", | |
| "use_cache": true, | |
| "vocab_size": 92544 | |
| } |