Text Generation
Transformers
Safetensors
English
llama
Llama-3-6B
6B
text-generation-inference
Inference Endpoints
Llama-3-6B-v0.1 / config.json
prince-canuma's picture
Upload LlamaForCausalLM
d2ce6fd verified
raw
history blame
699 Bytes
{
"_name_or_path": "prince-canuma/Llama-3-6B-v0",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128001,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 24,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.1",
"use_cache": true,
"vocab_size": 128256
}