初始化项目,由ModelHub XC社区提供模型

Model: Minami-su/Qwen1.5-0.5B-Chat_mistral
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-01 01:21:38 +08:00
commit d3f51d3d94
9 changed files with 454700 additions and 0 deletions

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"architectures": [
"MistralForCausalLM"
],
"attention_bias": true,
"attention_dropout": 0.0,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "mistral",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"rope_scaling": null,
"sliding_window": 32768,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.34.0.dev0",
"use_cache": true,
"use_sliding_window": true,
"vocab_size": 151936
}