OpenThinker2-32B / config.json
sedrickkeh's picture
Duplicate from mlfoundations-dev/DCFT-hero_run_2_fix_conversations-etash
274d459 verified
raw
history blame contribute delete
843 Bytes
{
"_name_or_path": "/leonardo_work/EUHPC_E03_068/eguha/models_cache/models--Qwen--Qwen2.5-32B-Instruct/snapshots/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd/",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 27648,
"max_position_embeddings": 32768,
"max_window_layers": 70,
"model_type": "qwen2",
"num_attention_heads": 40,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.46.1",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 152064
}