37 lines
930 B
JSON
37 lines
930 B
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"auto_map": {
|
||
|
|
"AutoConfig": "configuration_llama.LlamaConfig",
|
||
|
|
"AutoModel": "modeling_llama.LlamaModel",
|
||
|
|
"AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM"
|
||
|
|
},
|
||
|
|
"quant_mode": "w2_79a8kv8_embint4_mobilellm",
|
||
|
|
"is_w_quantized": true,
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"head_dim": 64,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 960,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 2560,
|
||
|
|
"max_position_embeddings": 8192,
|
||
|
|
"mlp_bias": false,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 15,
|
||
|
|
"num_hidden_layers": 32,
|
||
|
|
"num_key_value_heads": 5,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 20000.0,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.45.1",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 32000
|
||
|
|
}
|