Modelpublic

GeneZC/MiniChat-2-3B

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

24likes657downloads

config.json29 linesDownload Raw Back to root

1{2  "_name_or_path": "MiniChat-2-DPO-3B",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "bos_token_id": 1,7  "eos_token_id": 2,8  "hidden_act": "silu",9  "hidden_size": 3072,10  "initializer_range": 0.02,11  "intermediate_size": 8192,12  "max_position_embeddings": 4096,13  "model_type": "llama",14  "noisy_embedding_alpha": 5.0,15  "num_attention_heads": 24,16  "num_hidden_layers": 24,17  "num_key_value_heads": 24,18  "pad_token_id": 0,19  "pretraining_tp": 1,20  "rms_norm_eps": 1e-05,21  "rope_scaling": null,22  "rope_theta": 10000.0,23  "tie_word_embeddings": false,24  "torch_dtype": "float16",25  "transformers_version": "4.33.2",26  "use_cache": true,27  "vocab_size": 4921628}29