Files
llm-jp-4-8b-instruct-sansu/config.json
ModelHub XC eb39067829 初始化项目,由ModelHub XC社区提供模型
Model: ynakazat11/llm-jp-4-8b-instruct-sansu
Source: Original Platform
2026-05-28 15:11:22 +08:00

32 lines
795 B
JSON

{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"torch_dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 65536,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 500000,
"rope_type": "default"
},
"tie_word_embeddings": false,
"unsloth_version": "2026.5.2",
"use_cache": false,
"vocab_size": 196608
}