gradients-io-tournaments/augmented-9628c62b4208063a
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: gradients-io-tournaments/augmented-9628c62b4208063a
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-06 03:40:17 +08:00
commit d22c873529
11 changed files with 151971 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
config.json Normal file
View File

@@ -0,0 +1,61 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 8960,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 4096,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"pad_token_id": 151665,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "float16",
"transformers_version": "4.53.1",
"unsloth_fixed": true,
"use_cache": true,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 151936
}