初始化项目,由ModelHub XC社区提供模型

Model: sandbreak80sd/llm-350m-instruct
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-18 18:05:16 +08:00
commit 09ea00210f
10 changed files with 250906 additions and 0 deletions

23
config.json Normal file
View File

@@ -0,0 +1,23 @@
{
"architectures": [
"LlamaForCausalLM"
],
"model_type": "llama",
"hidden_size": 1024,
"intermediate_size": 2816,
"num_hidden_layers": 24,
"num_attention_heads": 16,
"num_key_value_heads": 4,
"hidden_act": "silu",
"max_position_embeddings": 2048,
"initializer_range": 0.02,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.0",
"vocab_size": 50304,
"bos_token_id": 50256,
"eos_token_id": 50256,
"pad_token_id": 50256
}