calme-2.4-rys-78b / config.json
MaziyarPanahi's picture
5157d80ee96a824b09ae5b1efb06d6b97b70ecb867dea6dc81fb4808d9e159bc
7703fc2 verified
raw
history blame
680 Bytes
{
"_name_or_path": "dnhkng/RYS-XLarge",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 29568,
"max_position_embeddings": 32768,
"max_window_layers": 80,
"model_type": "qwen2",
"num_attention_heads": 64,
"num_hidden_layers": 86,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.44.0.dev0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151646
}