TableLLM-CodeQwen-7B / config.json
BlackCatXJ's picture
Upload 12 files
19adac0 verified
raw
history blame contribute delete
700 Bytes
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 2,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 13440,
"max_position_embeddings": 65536,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000,
"rotary_emb_base": 1000000,
"seq_length": 65536,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.43.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 92416
}