File size: 1,275 Bytes
9c568ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct",
    "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,
    "model_type": "llama",
    "num_attention_heads": 64,
    "num_hidden_layers": 80,
    "num_key_value_heads": 8,
    "pretraining_tp": 1,
    "quantization_config": {
      "_load_in_4bit": true,
      "_load_in_8bit": false,
      "bnb_4bit_compute_dtype": "bfloat16",
      "bnb_4bit_quant_storage": "uint8",
      "bnb_4bit_quant_type": "nf4",
      "bnb_4bit_use_double_quant": true,
      "llm_int8_enable_fp32_cpu_offload": false,
      "llm_int8_has_fp16_weight": false,
      "llm_int8_skip_modules": null,
      "llm_int8_threshold": 6.0,
      "load_in_4bit": true,
      "load_in_8bit": false,
      "quant_method": "bitsandbytes"
    },
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 500000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.40.0",
    "use_cache": true,
    "vocab_size": 128256
  }