Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
mfromm's picture
Update config.json
e91cc26 verified
raw
history blame contribute delete
996 Bytes
{
"_name_or_path": "/home/Shared/align/models/teuken-instruct/7B_EU24_4T_EU24/train_run_24EU_teuken_commercial_EU24_lr_1e-5_2024_10_05_18_54_27/opengptx_checkpoints/checkpoint-405",
"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,
"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": true,
"vocab_size": 250680
}