trollek's picture
Update config.json
76a956d verified
raw
history blame contribute delete
No virus
669 Bytes
{
"_name_or_path": "trollek/danube2-1.8b-glaive-function-calling-v2",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 32000,
"eos_token_id": 32001,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 8192,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 24,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.41.2",
"use_cache": false,
"vocab_size": 32002
}