stablelm-zephyr-3b / config.json
jon-tow's picture
merge: upload transformers implementation (#13)
8b471c7 verified
raw
history blame contribute delete
599 Bytes
{
"architectures": [
"StableLmForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 0,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 4096,
"model_type": "stablelm",
"layer_norm_eps": 1e-05,
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"partial_rotary_factor": 0.25,
"rope_theta": 10000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.0",
"use_cache": true,
"use_qkv_bias": false,
"vocab_size": 50304
}