File size: 1,049 Bytes
419d040 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 |
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoTokenizer": [
"gptx_tokenizer.SPTokenizer",
null
]
},
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.0158,
"intermediate_size": 13440,
"max_position_embeddings": 4096,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 2,
"pad_token_id": 3,
"pretraining_tp": 1,
"quantization": {
"group_size": 64,
"bits": 4
},
"quantization_config": {
"group_size": 64,
"bits": 4
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": true,
"tokenizer_class": "SPTokenizer",
"torch_dtype": "bfloat16",
"transformers_version": "4.43.2",
"use_cache": false,
"vocab_size": 250680
} |