初始化项目,由ModelHub XC社区提供模型

Model: brady777/surfdoc-8b-v1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-06 15:01:18 +08:00
commit 6e9cd6757c
12 changed files with 666 additions and 0 deletions

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"torch_dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"max_position_embeddings": 40960,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"unsloth_version": "2026.3.4",
"use_cache": true,
"vocab_size": 151936
}