Text Generation
Transformers
Safetensors
Finnish
English
bloom
Inference Endpoints
text-generation-inference
Poro-34B / config.json
jonabur
add 600B checkpoints
dc0e31c
{
"_name_or_path": "/scratch/project_462000319/general-tools/checkpoints/33B_torch_step143712_bfloat16",
"apply_residual_connection_post_layernorm": false,
"architectures": [
"BloomForCausalLM"
],
"attention_dropout": 0.0,
"attention_softmax_in_fp32": true,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_dropout": 0.0,
"hidden_size": 7168,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"masked_softmax_fusion": true,
"model_type": "bloom",
"n_head": 56,
"n_layer": 54,
"pad_token_id": 3,
"pretraining_tp": 2,
"slow_but_exact": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.0",
"use_cache": true,
"vocab_size": 128000
}