初始化项目,由ModelHub XC社区提供模型

Model: InfiniAI/Megrez-3b-Instruct
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-16 21:31:33 +08:00
commit dfe433941f
24 changed files with 241129 additions and 0 deletions

31
config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"_name_or_path": "Megrez-3B-Instruct",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"eos_token_id": 120005,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 7168,
"max_position_embeddings": 32768,
"max_sequence_length": 32768,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 32,
"num_key_value_heads": 10,
"pad_token_id": 120002,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 5000000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.4",
"use_cache": true,
"vocab_size": 122880
}