Qwen2.5-Coder-7B / config.json
iiTzEddy's picture
Push model using huggingface_hub.
cb58af8 verified
raw
history blame contribute delete
200 Bytes
{
"n_embed": 3584,
"n_heads": 28,
"n_kv_heads": 4,
"n_layer": 28,
"n_mlp": 18944,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"tie_word_embeddings": false,
"vocab_size": 152064
}