Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
File size: 858 Bytes
6f37fc4
fb7cbbc
6f37fc4
 
 
 
 
 
 
 
 
 
 
 
 
fb7cbbc
6f37fc4
 
 
 
 
 
 
 
 
 
a0fd232
6f37fc4
 
 
 
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
{
  "_name_or_path": "/scratch/project_462000353/viking-checkpoints/converted_models/viking_v2_33B_iter_0476837_bfloat16",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 7168,
  "initializer_range": 0.02,
  "intermediate_size": 20480,
  "max_position_embeddings": 4096,
  "max_sequence_length": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 56,
  "num_hidden_layers": 56,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.37.2",
  "untie_embeddings_and_output_weights": true,
  "use_cache": true,
  "vocab_size": 131072
}