lbs1163's picture
chore: update batch llm config
12b7568 verified
Raw
History Blame Contribute Delete
1.3 kB
{
"architectures": [
"MobilintLlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "proxy_llama.MobilintLlamaConfig",
"AutoModelForCausalLM": "proxy_llama.MobilintLlamaForCausalLM"
},
"bos_token_id": 128000,
"dev_no": 0,
"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": 4096,
"mlp_bias": false,
"model_type": "mobilint-llama",
"mxq_path": "Llama-3.2-3B-Instruct-Batch16-W4V8.mxq",
"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": 2048,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"target_cores": [
"0:0",
"0:1",
"0:2",
"0:3",
"1:0",
"1:1",
"1:2",
"1:3"
],
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.45.0.dev0",
"use_cache": true,
"vocab_size": 128256,
"npu_prefill_chunk_size": {
"single": 128
},
"max_batch_size": 16
}