llama-1b-hf-32768-fpf / config.json
huseinzol05's picture
Upload LlamaForCausalLM
f4adf91
raw
history blame
628 Bytes
{
"_name_or_path": "fpf-1b-32k/checkpoint-17900",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 32768,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 4,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}