初始化项目,由ModelHub XC社区提供模型

Model: jiosephlee/e9-olmo2-13b-para9-expl-20260516
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-14 05:53:11 +08:00
commit 3bf16dd409
7 changed files with 500827 additions and 0 deletions

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"architectures": [
"Olmo2ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 100257,
"dtype": "bfloat16",
"eos_token_id": 100257,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "olmo2",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 100277,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 500000,
"rope_type": "default"
},
"tie_word_embeddings": false,
"transformers_version": "5.7.0",
"use_cache": false,
"vocab_size": 100352
}