初始化项目,由ModelHub XC社区提供模型

Model: nareshmeena12/fluxion-370m-instruct
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-10 16:59:18 +08:00
commit bd7228d2fc
7 changed files with 249571 additions and 0 deletions

17
config.json Normal file
View File

@@ -0,0 +1,17 @@
{
"architectures": [
"LlamaForCausalLM"
],
"model_type": "llama",
"vocab_size": 50000,
"hidden_size": 1024,
"intermediate_size": 3072,
"num_hidden_layers": 26,
"num_attention_heads": 16,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_theta": 500000.0,
"max_position_embeddings": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16"
}