初始化项目,由ModelHub XC社区提供模型

Model: gradients-io-tournaments/augmented-3d3bb39e2d570256
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 06:00:10 +08:00
commit 4c233c754f
8 changed files with 308 additions and 0 deletions

33
config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"architectures": [
"GemmaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"dtype": "bfloat16",
"eos_token_id": 1,
"head_dim": 256,
"hidden_act": "gelu",
"hidden_activation": null,
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 24576,
"max_position_embeddings": 8192,
"model_type": "gemma",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 16,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"tie_word_embeddings": true,
"transformers_version": "5.12.1",
"unsloth_version": "2024.9",
"use_bidirectional_attention": null,
"use_cache": false,
"vocab_size": 256000
}