初始化项目,由ModelHub XC社区提供模型

Model: sbintuitions/diafill-sarashina2.2-3b-instruct
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-18 19:30:34 +08:00
commit b309074e79
15 changed files with 410627 additions and 0 deletions

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 160,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 8960,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.53.0",
"use_cache": false,
"vocab_size": 102400
}