初始化项目,由ModelHub XC社区提供模型

Model: sail/Llama-3-Base-8B-DICE-Iter2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-10 11:55:55 +08:00
commit c4ea364711
13 changed files with 413081 additions and 0 deletions

28
config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "/home/aiops/chency/repo/alignment/results/dr/llama3-sft/data-mix/gamma-0.1/Llama3SFT-Data-Mix-0.1-Iter2",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128001,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.0",
"use_cache": false,
"vocab_size": 128256
}