GenC-LlaMa / config.json
Hieuman's picture
Upload LlamaEmbeddingLM
b5ccf02 verified
raw
history blame
737 Bytes
{
"_name_or_path": "output/edpo_msmarco_8b_v2/edpo_msmarco_8b_v2",
"architectures": [
"LlamaEmbeddingLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128009,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"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": "float32",
"transformers_version": "4.42.3",
"use_cache": false,
"vocab_size": 128256
}