sail
/

Text Generation
Transformers
Safetensors
qwen2
multilingual
sea
sailor
sft
chat
instruction
conversational
text-generation-inference
Sailor-4B-Chat / config.json
dreamerdeo's picture
Upload folder using huggingface_hub
8c9d53c verified
raw
history blame
662 Bytes
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 20,
"num_hidden_layers": 40,
"num_key_value_heads": 20,
"rms_norm_eps": 1e-06,
"rope_theta": 5000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}