初始化项目,由ModelHub XC社区提供模型

Model: OpenLLM-France/Luciole-1B-Base
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-01 08:37:18 +08:00
commit d5d44673db
28 changed files with 637202 additions and 0 deletions

30
config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"architectures": [
"NemotronForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"eos_token_id": 1,
"head_dim": 64,
"hidden_act": "relu2",
"hidden_size": 2048,
"initializer_range": 0.0134,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "nemotron",
"norm_eps": 1e-05,
"num_attention_heads": 32,
"num_hidden_layers": 24,
"num_key_value_heads": 8,
"partial_rotary_factor": 0.5,
"rope_theta": 2000000.0,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": true,
"vocab_size": 128000,
"training_steps": 1204876,
"training_tokens": 5053616226304
}