Text Generation
Safetensors
English
llama
INTELLECT-1-fp32 / config.json
samsja's picture
Upload folder using huggingface_hub (#1)
135959e verified
raw
history blame
749 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": [
128001,
128008,
128009
],
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 42,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"original_max_position_embeddings": 8192,
"rope_type": "default"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 128256
}