apollo-v1-7b / config.json
unmodeled-tyler's picture
๐Ÿš€ Apollo V1 7B: Advanced Reasoning Language Model - Complete model release with LoRA fine-tuned Mistral-7B-Instruct-v0.2, 161M parameter adapter, Apache 2.0 license, and professional documentation for logical, mathematical, and legal reasoning
a2897eb verified
raw
history blame contribute delete
992 Bytes
{
"_name_or_path": "vanta-research/apollo-v1-7b",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 32000,
"model_name": "Apollo V1 7B",
"version": "1.0.0",
"created_by": "VANTA Research",
"base_model": "mistralai/Mistral-7B-Instruct-v0.3",
"license": "MIT",
"model_description": "Advanced reasoning AI model specialized in logical reasoning, mathematical problem-solving, and legal analysis.",
"release_date": "2025-09-21T11:35:57.508765"
}