初始化项目,由ModelHub XC社区提供模型

Model: Almawave/Velvet-14B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-20 05:03:55 +08:00
commit 35a2d219d8
15 changed files with 263069 additions and 0 deletions

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 12544,
"max_position_embeddings": 131072,
"model_type": "mistral",
"num_attention_heads": 40,
"num_hidden_layers": 50,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"use_cache": false,
"vocab_size": 126976
}