qwen1.5-1.8b-sft / config.json
lewtun's picture
lewtun HF staff
Add HuggingFaceH4/qwen-1.5-1.8b-sft-v0.0 checkpoint
6eac95c verified
raw
history blame contribute delete
702 Bytes
{
"_name_or_path": "Qwen/Qwen1.5-1.8B",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5504,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151648
}