File size: 1,079 Bytes
fbfda8e |
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 |
{
"_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--abacusai--Llama-3-Giraffe-70B-Instruct/snapshots/8233a1af39365749cc08a942e09f0f489a7c2a11",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128001,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 4.0,
"type": "dynamic"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.41.1",
"use_cache": true,
"use_flash_attention_2": true,
"vocab_size": 128256
}
|