Files
Llama_3.1_8b_single_emb/config.json
ModelHub XC a4d495230d 初始化项目,由ModelHub XC社区提供模型
Model: ISTA-MLCV/Llama_3.1_8b_single_emb
Source: Original Platform
2026-06-16 22:54:20 +08:00

43 lines
1.1 KiB
JSON

{
"_name_or_path": "./models/llama_3.1_8b/pretrained_vanilla/train_checkpoints/SFTv110/from_base_run_11_fix/last",
"add_linear_shift": null,
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128009,
"gradual_rotation": null,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"learned_rotation": null,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 128011,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"rotation_alpha": null,
"rotation_direction": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.47.1",
"use_cache": false,
"vocab_size": 128256
}