Files
ModelHub XC 9b1711112b 初始化项目,由ModelHub XC社区提供模型
Model: ali-elganzory/Baguettotron-longsft_16k-SFT-Tulu3-decontaminated
Source: Original Platform
2026-04-28 08:30:06 +08:00

34 lines
779 B
JSON

{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 65492,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 576,
"initializer_range": 0.02,
"intermediate_size": 1536,
"max_position_embeddings": 16384,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 9,
"num_hidden_layers": 80,
"num_key_value_heads": 3,
"pad_token_id": 3,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 4.0,
"original_max_position_embeddings": 4096,
"rope_type": "yarn"
},
"rope_theta": 10000,
"tie_word_embeddings": true,
"transformers_version": "4.57.6",
"use_cache": true,
"vocab_size": 65600
}