初始化项目,由ModelHub XC社区提供模型

Model: Nanbeige/Nanbeige4-3B-Thinking-2510
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-10 00:10:25 +08:00
commit ca356fb59c
11 changed files with 368 additions and 0 deletions

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 166101,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 10496,
"max_position_embeddings": 65536,
"model_type": "llama",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 5000000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 166144
}