Tess-v2.5.2-Qwen2-72B / config.json
migtissera's picture
Upload folder using huggingface_hub
5719c28 verified
raw
history blame contribute delete
No virus
705 Bytes
{
"_name_or_path": "/home/migel/Tess-v2.5-qwen2-72B-safetensors",
"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": 131072,
"max_window_layers": 80,
"model_type": "qwen2",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.41.1",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 152064
}