Files
Llama-3.2-3B-Instruct/config.json
ai-modelscope becaf541ea Upload folder using huggingface_hub (#1)
- 86863a0d4cadd8b2d4359d81b858ed66f9c7e755f4839c9a755e802bda5c1286 (38b8179a8968726eb48a75566a1e623b03f4d622)
- d6dc246fe07102fed432d38186a030469a6b99b7825bd273a907497008741b95 (012f47224a8b355469cb2bce94ec3ac1ec0f2b17)
2024-12-20 16:20:05 +08:00

39 lines
969 B
JSON

{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": [
128001,
128008,
128009
],
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 24,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 32.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.45.0.dev0",
"use_cache": true,
"vocab_size": 128256
}