23 lines
580 B
JSON
23 lines
580 B
JSON
{
|
|
"architectures": ["Qwen2ForCausalLM"],
|
|
"model_type": "qwen2",
|
|
"vocab_size": 151936,
|
|
"hidden_size": 1536,
|
|
"intermediate_size": 8960,
|
|
"num_hidden_layers": 28,
|
|
"num_attention_heads": 12,
|
|
"num_key_value_heads": 2,
|
|
"max_position_embeddings": 32768,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.37.0",
|
|
"_name_or_path": "WeiboAI/VibeThinker-1.5B",
|
|
"use_cache": true,
|
|
"tie_word_embeddings": false,
|
|
"rope_theta": 1000000.0,
|
|
"quantization_config": {
|
|
"quantum_kernel": true,
|
|
"ibm_backend": "ibm_fez",
|
|
"qubits": 2,
|
|
"shots": 8192
|
|
}
|
|
} |