Files
ModelHub XC 0b4a891589 初始化项目,由ModelHub XC社区提供模型
Model: tergel/qwen2.5-math-1.5b-instruct-gsm8k-fs-gpt4o-bon
Source: Original Platform
2026-09-23 12:19:27 +08:00

30 lines
821 B
JSON

{
"_name_or_path": "/data/tergel/models/trained/hybrid_mixed/qwen2.5-math-1.5b-instruct/gsm8k/ft_16_shift_fs_gpt4o_16/ckpts/checkpoint-463",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 8960,
"max_position_embeddings": 4096,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}