初始化项目,由ModelHub XC社区提供模型

Model: opencsg/csg-wukong-1B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-26 10:53:58 +08:00
commit 12399c8927
9 changed files with 93618 additions and 0 deletions

24
config.json Normal file
View File

@@ -0,0 +1,24 @@
{
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 22,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.37.2",
"use_cache": true,
"vocab_size": 32000
}