Files
ModelHub XC 3c340f684e 初始化项目,由ModelHub XC社区提供模型
Model: OpenAssistant/pythia-12b-sft-v8-2.5k-steps
Source: Original Platform
2026-07-19 07:13:10 +08:00

26 lines
638 B
JSON

{
"_name_or_path": ".saved/pythia-12b-sft8/checkpoint-2500/",
"architectures": [
"GPTNeoXForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 0,
"hidden_act": "gelu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 20480,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 40,
"num_hidden_layers": 36,
"rotary_emb_base": 10000,
"rotary_pct": 0.25,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.0.dev0",
"use_cache": true,
"use_parallel_residual": true,
"vocab_size": 50288
}