Text Generation
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
LLaMA-7B-EN-Chat-40k / config.json
zhijianma's picture
Upload LlamaForCausalLM
d716d2d
raw
history blame
773 Bytes
{
"_name_or_path": "/root/zhijian.mzj/data-juicer-sft/llama-7b_en_sft_hist_ratio_40k",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 2048,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 32000,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.34.1",
"unk_token_id": 0,
"use_cache": true,
"vocab_size": 32001
}