Tess-7B-v2.0 / config.json
migtissera's picture
Set sliding window to null to match Mistral-7B-Instruct-v0.2 (#4)
1b72f7b verified
{
"_name_or_path": "/home/migel/models/Tesoro-7B-2B/merged",
"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": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.38.0.dev0",
"use_cache": false,
"vocab_size": 32000
}