17 lines
589 B
JSON
17 lines
589 B
JSON
|
{
|
||
|
|
"source_checkpoint_dir": "/dir1/llm_corpus/checkpoints/dante_2b_instruct_v2/final_hf",
|
||
|
|
"project_dir": "/home/angeletti/project_slm",
|
||
|
|
"output_dir": "/dir1/llm_corpus/checkpoints/dante_2b_instruct_v2/final_transformers",
|
||
|
|
"source_weight_file": "model.bin",
|
||
|
|
"target_architecture": "LlamaForCausalLM",
|
||
|
|
"safe_serialization": true,
|
||
|
|
"dtype": "bfloat16",
|
||
|
|
"num_layers": 28,
|
||
|
|
"hidden_size": 2560,
|
||
|
|
"num_attention_heads": 20,
|
||
|
|
"num_key_value_heads": 4,
|
||
|
|
"intermediate_size": 6912,
|
||
|
|
"max_position_embeddings": 4096,
|
||
|
|
"rope_theta": 10000.0,
|
||
|
|
"tokenizer_model_max_length": 4096
|
||
|
|
}
|