jiangcongtao's picture
Trained with Unsloth
50fa4df verified
raw
history blame contribute delete
791 Bytes
{
"_name_or_path": "unsloth/qwen2-0.5b-bnb-4bit",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"pad_token_id": 151646,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "float16",
"transformers_version": "4.42.3",
"unsloth_version": "2024.7",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}