CoolFace
Modelpublic

Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes10downloads
config.json29 linesDownload Raw Back to root
1{2  "_name_or_path": "nvidia/Mistral-NeMo-Minitron-8B-Base",3  "activation": "silu",4  "architectures": [5    "MistralForCausalLM"6  ],7  "attention_dropout": 0.0,8  "bos_token_id": 1,9  "eos_token_id": 2,10  "head_dim": 128,11  "hidden_act": "silu",12  "hidden_size": 4096,13  "initializer_range": 0.02,14  "intermediate_size": 11520,15  "max_position_embeddings": 8192,16  "model_type": "mistral",17  "num_attention_heads": 32,18  "num_hidden_layers": 40,19  "num_key_value_heads": 8,20  "rms_norm_eps": 1e-05,21  "rope_theta": 1000000.0,22  "sliding_window": null,23  "tie_word_embeddings": false,24  "torch_dtype": "bfloat16",25  "transformers_version": "4.40.2",26  "use_cache": true,27  "vocab_size": 13107228}29