Files
ModelHub XC 481b60ebf1 初始化项目,由ModelHub XC社区提供模型
Model: allegrolab/hubble-8b-500b_toks-perturbed-hf
Source: Original Platform
2026-08-07 18:27:19 +08:00

30 lines
684 B
JSON

{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 50279,
"eos_token_id": 50279,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 2048,
"mlp_bias": true,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.53.2",
"use_cache": true,
"vocab_size": 50304
}