初始化项目,由ModelHub XC社区提供模型

Model: SupraLabs/Supra-1.5-50M-base-exp
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-09 02:22:04 +08:00
commit 7d4e257a40
9 changed files with 226 additions and 0 deletions

38
config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"dtype": "float32",
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 512,
"initializer_range": 0.02,
"intermediate_size": 1408,
"max_position_embeddings": 5120,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 8,
"num_hidden_layers": 12,
"num_key_value_heads": 4,
"pad_token_id": 1,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"factor": 1.0,
"rope_theta": 10000,
"rope_type": "linear"
},
"rope_scaling": {
"factor": 1.0,
"type": "linear"
},
"rope_theta": 10000.0,
"tie_word_embeddings": true,
"transformers_version": "4.57.6",
"use_cache": false,
"vocab_size": 32000
}