ProbLLMs/DPO_Reference

1{
2  "_name_or_path": "deepseek-ai/deepseek-math-7b-rl",
3  "architectures": [
4    "LlamaForCausalLM"
5  ],
6  "attention_bias": false,
7  "attention_dropout": 0.0,
8  "bos_token_id": 100000,
9  "eos_token_id": 100001,
10  "hidden_act": "silu",
11  "hidden_size": 4096,
12  "initializer_range": 0.02,
13  "intermediate_size": 11008,
14  "max_position_embeddings": 4096,
15  "model_type": "llama",
16  "moe_intermediate_size": 11008,
17  "num_attention_heads": 32,
18  "num_hidden_layers": 30,
19  "num_key_value_heads": 32,
20  "pretraining_tp": 1,
21  "rms_norm_eps": 1e-06,
22  "rope_scaling": null,
23  "rope_theta": 10000,
24  "tie_word_embeddings": false,
25  "torch_dtype": "float32",
26  "transformers_version": "4.40.2",
27  "use_cache": true,
28  "vocab_size": 102400
29}
30