ForSureTesterSim's picture
Upload config.json with huggingface_hub
de6110c verified
Raw
History Blame Contribute Delete
1.25 kB
{
"transformers_version": "5.14.1",
"architectures": [
"TransLlamaForCausalLM"
],
"output_hidden_states": false,
"return_dict": true,
"dtype": "bfloat16",
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"problem_type": null,
"vocab_size": 128256,
"hidden_size": 4096,
"intermediate_size": 14336,
"num_hidden_layers": 32,
"num_attention_heads": 32,
"num_key_value_heads": 8,
"hidden_act": "silu",
"max_position_embeddings": 131072,
"initializer_range": 0.02,
"rms_norm_eps": 1e-05,
"use_cache": false,
"pad_token_id": null,
"bos_token_id": 128000,
"eos_token_id": 128001,
"pretraining_tp": 1,
"tie_word_embeddings": false,
"rope_parameters": {
"factor": 8.0,
"low_freq_factor": 1.0,
"high_freq_factor": 4.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3",
"rope_theta": 500000.0
},
"attention_bias": false,
"attention_dropout": 0.0,
"mlp_bias": false,
"head_dim": 128,
"_name_or_path": "meta-llama/Llama-3.1-8B",
"model_type": "llama",
"output_attentions": false,
"kv_lora_rank": 512,
"qk_rope_head_dim": 64
}