Files
zephyr-smol_llama-100m-sft-…/config.json
ModelHub XC 1e1cc416e3 初始化项目,由ModelHub XC社区提供模型
Model: peft-internal-testing/zephyr-smol_llama-100m-sft-full
Source: Original Platform
2026-05-15 23:59:05 +08:00

33 lines
729 B
JSON

{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": 32,
"hidden_act": "silu",
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 1024,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 24,
"num_hidden_layers": 6,
"num_key_value_heads": 8,
"pad_token_id": null,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"tie_word_embeddings": false,
"transformers_version": "5.3.0.dev0",
"use_cache": false,
"vocab_size": 32128
}